Look up dot in Wiktionary, the free dictionary.

Dot, DoT or DOT may refer to:

Typography[link]

• Full stop, also called period in American English, used as a sentence terminator and as a decimal separator (decimal point) in numerals ( . )
• Interpunct, between words, also called middle dot, centered dot, and Georgian comma ( · )
  • dot operator, used as notation for multiplication ( ⋅ )
  • word separator middle dot, used in Avestan, Samaritan ( ⸱ )
  • Katakana middle dot ( ・ )
• Dot (diacritic), above or below a character (e.g. ȧ, ạ, İ, Ċ, ċ, etc.) ( ˙  ̣ ﮲ ﮳ )
  • Hebrew shin and sin dots ( ׁ  ׂ) as well as upper and lower dots (  ׄ  ׅ )
  • Syriac feminine dot (  ݀ )
  • Devanagari high spacing dot ( ॱ )
  • Myanmar dot below (  ့ )
  • Canadian syllabics final middle dot ( ᐧ )
  • Canadian syllabics final raised dot ( ᣟ )
  • Vedic tone dot below (  ᳝)
  • One dot leader, also used as Armenian semi-colon ( ․ )
  • The dot above is used to denote time derivation, in Newtonian notation
  • There are also double, triple, quadruple and even quintuple diacritic dots
• Dotted note, in music notation (  𝅭 )

Entertainment[link]

• Dot (song), a single by the Los Angeles pop punk band ALL
• Dot (MADtv character), a fictional character on the television show MADtv
• Dot, A Drama in Three Acts, an 1859 stage adaption of the book The Cricket on the Hearth by Charles Dickens
• Dot and Dash, an animated girl and animated boy appearing as the PBS idents
• Dot and the Kangaroo, a children's book by Ethel C. Pedley, written in 1899
• Dot Branning, fictional character on the television show EastEnders
• Dot Dot Dot (magazine), a magazine publication
• Dot Matrix (ReBoot), fictional character on the television series ReBoot
• Dot Moore (1914–2007), television personality in Mobile, Alabama
• Little Dot, a comic book character
• Yakko, Wakko, and Dot, characters from the animated television show Animaniacs

Companies and agencies[link]

• Department for Transport, in the UK, formerly the Department of Transport (DoT)
• Department of Telecommunications, India
• Department of Tourism (Philippines)
• Department of Transportation, in the United States and various U.S. states
• Dot Cycle and Motor Manufacturing Company, a British motorcycle manufacturing company
• Dot Records, an American company

Technology[link]

• Dot, an element in Morse code
• Dot (Unix)
• DOT language, in computation, the plain-text format for describing graphs used by Graphviz software
• Dot matrix, a 2-dimensional array of dots used to generate characters, symbols and images
• Damage over time, in computer and video games
• Designated Order Turnaround or SuperDot, an electronic system used by NYSE to route market orders
• Diffuse optical tomography, an imaging technique
• Directly observed treatment, a way to administer medicine
• Dissolved oxygen tension (DOT)
• Epiphone Dot, a series of archtop guitars
• "." may refer to the DNS root zone, the root domain of the Domain Name System
• Dutch Open Telescope

Other uses[link]

• Dot, a diminutive form of the given name Dorothy
• Dot (mango), a mango cultivar from Florida
• The Dot, a children's picture book
• The Dot, an Office Assistant, one of several interactive animated characters available in Microsoft Office
• The Dot (restaurant), a fictional café in Degrassi: The Next Generation
• Dot product, in mathematics
• Dictionary of Occupational Titles
• Newton's notation for differentiation, in mathematics and physics
• Tropical Storm Dot (disambiguation), several tropical storms

See also[link]

• Dots (disambiguation)
• Dot notation (disambiguation)

This disambiguation page lists articles associated with the same title. If an internal link led you here, you may wish to change the link to point directly to the intended article.

In computational linguistics, word-sense disambiguation (WSD) is an open problem of natural language processing, which governs the process of identifying which sense of a word (i.e. meaning) is used in a sentence, when the word has multiple meanings (polysemy). The solution to this problem impacts other computer-related writing, such as discourse, improving relevance of search engines, anaphora resolution, coherence, inference et cetera.

Research has progressed steadily to the point where WSD systems achieve sufficiently high levels of accuracy on a variety of word types and ambiguities. A rich variety of techniques have been researched, from dictionary-based methods that use the knowledge encoded in lexical resources, to supervised machine learning methods in which a classifier is trained for each distinct word on a corpus of manually sense-annotated examples, to completely unsupervised methods that cluster occurrences of words, thereby inducing word senses. Among these, supervised learning approaches have been the most successful algorithms to date.

Current accuracy is difficult to state without a host of caveats. In English, accuracy at the coarse-grained (homograph) level is routinely above 90%, with some methods on particular homographs achieving over 96%. On finer-grained sense distinctions, top accuracies from 59.1% to 69.0% have been reported in recent evaluation exercises (SemEval-2007, Senseval-2), where the baseline accuracy of the simplest possible algorithm of always choosing the most frequent sense was 51.4% and 57%, respectively.

About[link]

A disambiguation process requires two strict things: a dictionary to specify the senses which are to be disambiguated and a corpus of language data to be disambiguated (in some methods, a training corpus of language examples is also required). WSD task has two variants: "lexical sample" and "all words" task. The former comprises disambiguating the occurrences of a small sample of target words which were previously selected, while in the latter all the words in a piece of running text need to be disambiguated. The latter is deemed a more realistic form of evaluation, but the corpus is more expensive to produce because human annotators have to read the definitions for each word in the sequence every time they need to make a tagging judgement, rather than once for a block of instances for the same target word.

To give a hint how all this works, consider two examples of the distinct senses that exist for the (written) word "bass":

1. a type of fish
2. tones of low frequency

and the sentences:

1. I went fishing for some sea bass.
2. The bass line of the song is too weak.

To a human, it is obvious that the first sentence is using the word "bass (fish)", as in the former sense above and in the second sentence, the word "bass (instrument)" is being used as in the latter sense below. Developing algorithms to replicate this human ability can often be a difficult task, as is further exemplified by the implicit equivocation between "bass (sound)" and "bass" (musical instrument).

History[link]

WSD was first formulated as a distinct computational task during the early days of machine translation in the 1940s, making it one of the oldest problems in computational linguistics. Warren Weaver, in his famous 1949 memorandum on translation,^[1] first introduced the problem in a computational context. Early researchers understood the significance and difficulty of WSD well. In fact, Bar-Hillel (1960) used the above example to argue^[2] that WSD could not be solved by "electronic computer" because of the need in general to model all world knowledge.

In the 1970s, WSD was a subtask of semantic interpretation systems developed within the field of artificial intelligence, but since WSD systems were largely rule-based and hand-coded they were prone to a knowledge acquisition bottleneck.

By the 1980s large-scale lexical resources, such as the Oxford Advanced Learner's Dictionary of Current English (OALD), became available: hand-coding was replaced with knowledge automatically extracted from these resources, but disambiguation was still knowledge-based or dictionary-based.

In the 1990s, the statistical revolution swept through computational linguistics, and WSD became a paradigm problem on which to apply supervised machine learning techniques.

The 2000s saw supervised techniques reach a plateau in accuracy, and so attention has shifted to coarser-grained senses, domain adaptation, semi-supervised and unsupervised corpus-based systems, combinations of different methods, and the return of knowledge-based systems via graph-based methods. Still, supervised systems continue to perform best.

Difficulties[link]

Differences between dictionaries[link]

One problem with word sense disambiguation is deciding what the senses are. In cases like the word bass above, at least some senses are obviously different. In other cases, however, the different senses can be closely related (one meaning being a metaphorical or metonymic extension of another), and in such cases division of words into senses becomes much more difficult. Different dictionaries and thesauruses will provide different divisions of words into senses. One solution some researchers have used is to choose a particular dictionary, and just use its set of senses. Generally, however, research results using broad distinctions in senses have been much better than those using narrow ones.^[3][4] However, given the lack of a full-fledged coarse-grained sense inventory, most researchers continue to work on fine-grained WSD.

Most research in the field of WSD is performed by using WordNet as a reference sense inventory for English. WordNet is a computational lexicon that encodes concepts as synonym sets (e.g. the concept of car is encoded as { car, auto, automobile, machine, motorcar }). Other resources used for disambiguation purposes include Roget's Thesaurus^[5] and Wikipedia.^[6]

Part-of-speech tagging[link]

In any real test, part-of-speech tagging and sense tagging are very closely related with each potentially making constraints to the other. And the question whether these tasks should be kept together or decoupled is still not unanimously resolved, but recently scientists incline to test these things separately (e.g. in the Senseval/SemEval competitions parts of speech are provided as input for the text to disambiguate).

It is instructive to compare the word sense disambiguation problem with the problem of part-of-speech tagging. Both involve disambiguating or tagging with words, be it with senses or parts of speech. However, algorithms used for one do not tend to work well for the other, mainly because the part of speech of a word is primarily determined by the immediately adjacent one to three words, whereas the sense of a word may be determined by words further away. The success rate for part-of-speech tagging algorithms is at present much higher than that for WSD, state-of-the art being around 95% accuracy or better, as compared to less than 75% accuracy in word sense disambiguation with supervised learning. These figures are typical for English, and may be very different from those for other languages.

Inter-judge variance[link]

Another problem is inter-judge variance. WSD systems are normally tested by having their results on a task compared against those of a human. However, while it is relatively easy to assign parts of speech to text, training people to tag senses is far more difficult.^[7] While users can memorize all of the possible parts of speech a word can take, it is often impossible for individuals to memorize all of the senses a word can take. Moreover, humans do not agree on the task at hand – give a list of senses and sentences, and humans will not always agree on which word belongs in which sense.^[8]

Thus, a computer cannot be expected to give better performance on such a task than a human (indeed, since the human serves as the standard, the computer being better than the human is incoherent),^{[citation needed]} so the human performance serves as an upper bound. Human performance, however, is much better on coarse-grained than fine-grained distinctions, so this again is why research on coarse-grained distinctions^[9][10] has been put to test in recent WSD evaluation exercises.^[3][4]

Common sense[link]

Some AI researchers like Douglas Lenat argue that one cannot parse meanings from words without some form of common sense ontology. For example, comparing these two sentences:

• "Jill and Mary are sisters." – (they are sisters of each other).
• "Jill and Mary are mothers." – (each is independently a mother).

To properly identify senses of words one must know common sense facts.^[11] Moreover, sometimes the common sense is needed to disambiguate such words like pronouns in case of having anaphoras or cataphoras in the text.

Sense inventory and algorithms' task-dependency[link]

A task-independent sense inventory is not a coherent concept^[12]: each task requires its own division of word meaning into senses relevant to the task. For example, the ambiguity of 'mouse' (animal or device) is not relevant in English-French machine translation, but is relevant in information retrieval. The opposite is true of 'river', which requires a choice in French (fleuve 'flows into the sea', or rivière 'flows into a river').

Also, completely different algorithms might be required by different applications. In machine translation, the problem takes the form of target word selection. Here, the "senses" are words in the target language, which often correspond to significant meaning distinctions in the source language ("bank" could translate to the French "banque" -- that is, 'financial bank' or "rive" -- that is, 'edge of river'). In information retrieval, a sense inventory is not necessarily required, because it is enough to know that a word is used in the same sense in the query and a retrieved document; what sense that is, is unimportant.

Discreteness of senses[link]

Finally, the very notion of "word sense" is slippery and controversial. Most people can agree in distinctions at the coarse-grained homograph level (e.g., pen as writing instrument or enclosure), but go down one level to fine-grained polysemy, and disagreements arise. For example, in Senseval-2, which used fine-grained sense distinctions, human annotators agreed in only 85% of word occurrences.^[13] Word meaning is in principle infinitely variable and context sensitive. It does not divide up easily into distinct or discrete sub-meanings.^[14] Lexicographers frequently discover in corpora loose and overlapping word meanings, and standard or conventional meanings extended, modulated, and exploited in a bewildering variety of ways. The art of lexicography is to generalize from the corpus to definitions that evoke and explain the full range of meaning of a word, making it seem like words are well-behaved semantically. However, it is not at all clear if these same meaning distinctions are applicable in computational applications, as the decisions of lexicographers are usually driven by other considerations. Recently, a task – named lexical substitution – has been proposed as a possible solution to the sense discreteness problem.^[15] The task consists of providing a substitute for a word in context that preserves the meaning of the original word (potentially, substitutes can be chosen from the full lexicon of the target language, thus overcoming discreteness).

Approaches and methods[link]

As in all natural language processing, there are two main approaches to WSD – deep approaches and shallow approaches.

Deep approaches presume access to a comprehensive body of world knowledge. Knowledge, such as "you can go fishing for a type of fish, but not for low frequency sounds" and "songs have low frequency sounds as parts, but not types of fish", is then used to determine in which sense the word is used. These approaches are not very successful in practice, mainly because such a body of knowledge does not exist in a computer-readable format, outside of very limited domains.^[16] However, if such knowledge did exist, then deep approaches would be much more accurate than the shallow approaches.^{[citation needed]} Also, there is a long tradition in computational linguistics, of trying such approaches in terms of coded knowledge and in some cases, it is hard to say clearly whether the knowledge involved is linguistic or world knowledge. The first attempt was that by Margaret Masterman and her colleagues, at the Cambridge Language Research Unit in England, in the 1950s. This attempt used as data a punched-card version of Roget's Thesaurus and its numbered "heads", as an indicator of topics and looked for repetitions in text, using a set intersection algorithm. It was not very successful,^[17] but had strong relationships to later work, especially Yarowsky's machine learning optimisation of a thesaurus method in the 1990s.

Shallow approaches don't try to understand the text. They just consider the surrounding words, using information such as "if bass has words sea or fishing nearby, it probably is in the fish sense; if bass has the words music or song nearby, it is probably in the music sense." These rules can be automatically derived by the computer, using a training corpus of words tagged with their word senses. This approach, while theoretically not as powerful as deep approaches, gives superior results in practice, due to the computer's limited world knowledge. However, it can be confused by sentences like The dogs bark at the tree which contains the word bark near both tree and dogs.

There are four conventional approaches to WSD:

• Dictionary- and knowledge-based methods: These rely primarily on dictionaries, thesauri, and lexical knowledge bases, without using any corpus evidence.
• Supervised methods: These make use of sense-annotated corpora to train from.
• Semi-supervised or minimally supervised methods: These make use of a secondary source of knowledge such as a small annotated corpus as seed data in a bootstrapping process, or a word-aligned bilingual corpus.
• Unsupervised methods: These eschew (almost) completely external information and work directly from raw unannotated corpora. These methods are also known under the name of word sense discrimination.

Almost all these approaches normally work by defining a window of n content words around each word to be disambiguated in the corpus, and statistically analyzing those n surrounding words. Two shallow approaches used to train and then disambiguate are Naïve Bayes classifiers and decision trees. In recent research, kernel-based methods such as support vector machines have shown superior performance in supervised learning. Graph-based approaches have also gained much attention from the research community, and currently achieve performance close to the state of the art.

Dictionary- and knowledge-based methods[link]

The Lesk algorithm^[18] is the seminal dictionary-based method. It is based on the hypothesis that words used together in text are related to each other and that the relation can be observed in the definitions of the words and their senses. Two (or more) words are disambiguated by finding the pair of dictionary senses with the greatest word overlap in their dictionary definitions. For example, when disambiguating the words in "pine cone", the definitions of the appropriate senses both include the words evergreen and tree (at least in one dictionary).

An alternative to the use of the definitions is to consider general word-sense relatedness and to compute the semantic similarity of each pair of word senses based on a given lexical knowledge base such as WordNet. Graph-based methods reminiscent of spreading activation research of the early days of AI research have been applied with some success. More complex graph-based approaches have been shown to perform almost as well as supervised methods^[19] or even outperforming them on specific domains.^[3][20] Recently, it has been reported that simple graph connectivity measures, such as degree, perform state-of-the-art WSD in the presence of a sufficiently rich lexical knowledge base.^[21] Also, automatically transferring knowledge in the form of semantic relations from Wikipedia to WordNet has been shown to boost simple knowledge-based methods, enabling them to rival the best supervised systems and even outperform them in a domain-specific setting.^[22]

The use of selectional preferences (or selectional restrictions) is also useful, for example, knowing that one typically cooks food, one can disambiguate the word bass in "I am cooking basses" (i.e., it's not a musical instrument).

Supervised methods[link]

Supervised methods are based on the assumption that the context can provide enough evidence on its own to disambiguate words (hence, world knowledge and reasoning are deemed unnecessary). Probably every machine learning algorithm going has been applied to WSD, including associated techniques such as feature selection, parameter optimization, and ensemble learning. Support Vector Machines and memory-based learning have been shown to be the most successful approaches, to date, probably because they can cope with the high-dimensionality of the feature space. However, these supervised methods are subject to a new knowledge acquisition bottleneck since they rely on substantial amounts of manually sense-tagged corpora for training, which are laborious and expensive to create.

Semi-supervised methods[link]

Because of the lack of training data, many word sense disambiguation algorithms use semi-supervised learning, which allows both labeled and unlabeled data. The Yarowsky algorithm was an early example of such an algorithm.^[23] It uses the ‘One sense per collocation’ and the ‘One sense per discourse’ properties of human languages for word sense disambiguation. From observation, words tend to exhibit only one sense in most given discourse and in a given collocation.

The bootstrapping approach starts from a small amount of seed data for each word: either manually tagged training examples or a small number of surefire decision rules (e.g., 'play' in the context of 'bass' almost always indicates the musical instrument). The seeds are used to train an initial classifier, using any supervised method. This classifier is then used on the untagged portion of the corpus to extract a larger training set, in which only the most confident classifications are included. The process repeats, each new classifier being trained on a successively larger training corpus, until the whole corpus is consumed, or until a given maximum number of iterations is reached.

Other semi-supervised techniques use large quantities of untagged corpora to provide co-occurrence information that supplements the tagged corpora. These techniques have the potential to help in the adaptation of supervised models to different domains.

Also, an ambiguous word in one language is often translated into different words in a second language depending on the sense of the word. Word-aligned bilingual corpora have been used to infer cross-lingual sense distinctions, a kind of semi-supervised system.

Unsupervised methods[link]

Unsupervised learning is the greatest challenge for WSD researchers. The underlying assumption is that similar senses occur in similar contexts, and thus senses can be induced from text by clustering word occurrences using some measure of similarity of context,^[24] a task referred to as word sense induction or discrimination. Then, new occurrences of the word can be classified into the closest induced clusters/senses. Performance has been lower than other methods, above, but comparisons are difficult since senses induced must be mapped to a known dictionary of word senses. If a mapping to a set of dictionary senses is not desired, cluster-based evaluations (including measures of entropy and purity) can be performed. Alternatively, word sense induction methods can be tested and compared within an application. For instance, it has been shown that word sense induction improves Web search result clustering by increasing the quality of result clusters and the degree diversification of result lists.^[25] It is hoped that unsupervised learning will overcome the knowledge acquisition bottleneck because they are not dependent on manual effort.

Other approaches[link]

Other approaches may vary differently in their methods:

• Identification of dominant word senses;^[26][27][28]
• Domain-driven disambiguation;^[29][30]
• WSD using Cross-Lingual Evidence.^[31][32]

Local impediments and summary[link]

The knowledge acquisition bottleneck is perhaps the major impediment to solving the WSD problem. Unsupervised methods rely on knowledge about word senses, which is barely formulated in dictionaries and lexical databases. Supervised methods depend crucially on the existence of manually annotated examples for every word sense, a requisite that can so far be met only for a handful of words for testing purposes, as it is done in the Senseval exercises.

Therefore, one of the most promising trends in WSD research is using the largest corpus ever accessible, the World Wide Web, to acquire lexical information automatically.^[33] WSD has been traditionally understood as an intermediate language engineering technology which could improve applications such as information retrieval (IR). In this case, however, the reverse is also true: Web search engines implement simple and robust IR techniques that can be successfully used when mining the Web for information to be employed in WSD. Therefore, the lack of training data provoked appearing some new algorithms and techniques described here:

External knowledge sources[link]

Knowledge is a fundamental component of WSD. Knowledge sources provide data which are essential to associate senses with words. They can vary from corpora of texts, either unlabeled or annotated with word senses, to machine-readable dictionaries, thesauri, glossaries, ontologies, etc. They can be^[34][35] classified as follows:

1. Structured:
   • Thesauri
   • Machine-readable dictionaries (MRDs)
   • Ontologies
2. Unstructured:
   • Corpora: raw corpora and sense-annotated corpora
   • Collocation resources
   • Other resources (such as word frequency lists, stoplists, domain labels,^[36] etc.)

Evaluation[link]

Comparing and evaluating different WSD systems is extremely difficult, because of the different test sets, sense inventories, and knowledge resources adopted. Before the organization of specific evaluation campaigns most systems were assessed on in-house, often small-scale, data sets. In order to test one's algorithm, developers should spend their time to annotate all word occurrences. And comparing methods even on the same corpus is not eligible if there is different sense inventories.

In order to define common evaluation datasets and procedures, public evaluation campaigns have been organized. Senseval (now renamed SemEval) is an international word sense disambiguation competition, held every three years since 1998: Senseval-1 (1998), Senseval-2 (2001), Senseval-3 (2004), and its successor, SemEval (2007). The objective of the competition is to organize different lectures, preparing and hand-annotating corpus for testing systems, perform a comparative evaluation of WSD systems in several kinds of tasks, including all-words and lexical sample WSD for different languages, and, more recently, new tasks such as semantic role labeling, gloss WSD, lexical substitution, etc. The systems submitted for evaluation to these competitions usually integrate different techniques and often combine supervised and knowledge-based methods (especially for avoiding bad performance in lack of training examples).

Task Design Choices[link]

Sense Inventories. During the first Senseval workshop the HECTOR sense inventory was adopted. The reason for adopting a previously unknown sense inventory was mainly to avoid the use of popular fine-grained word senses (such as WordNet), which could make the experiments unfair or biased. However, given the lack of coverage of such inventories, since the second Senseval workshop the WordNet sense inventory has been adopted.

A set of testing words. Comparison of methods can be divided in 2 groups by amount of words to test. The difference consists in the amount of analysis and processing:

• all-words task implies disambiguating all the words of the text
• lexical sample consists in disambiguating some previously chosen target words.

It is assumed that the former one is more realistic evaluation, although with very laborious testing of results. Initially only the latter was used in evaluation but later the former was included.

Lexical sample organizers had to choose samples on which the systems were to be tested. A criticism of earlier forays into lexical-sample WSD evaluation is that the lexical sample had been chosen according to the whim of the experimenter (or, to coincide with earlier experimenters' selections). For English Senseval, a sampling frame was devised in which words were classified according to their frequency (in the BNC) and their polysemy level (in WordNet). Also, inclusion POS-tagging problem was a matter of discussion and it was decided that samples should be words with known part of speech and some indeterminants (for ex. 15 noun tasks, 13 verb tasks, 8 adjectives, and 5 indeterminates).

Baselines. For comparison purposes, known, yet simple, algorithms named baselines are used. These include different variants of Lesk algorithm or most frequent sense algorithm.

Sense inventory. WSD exercises require a dictionary, to specify the word senses which are to be disambiguated, and a corpus of language data to be disambiguated. WordNet is the most popular example of sense inventory. The reason for adopting the HECTOR database during Senseval-1 was that the WordNet inventory was already publicly available.^[37]

Evaluation measures. During the evaluation of WSD systems two main performance measures are used:

• Precision: the fraction of system assignments made that are correct
• Recall: the fraction of total word instances correctly assigned by a system

If a system makes an assignment for every word, then precision and recall are the same, and can be called accuracy. This model has been extended to take into account systems that return a set of senses with weights for each occurrence.

Software[link]

• WordNet::SenseRelate, is a project that includes free, open source systems for word sense disambiguation and lexical sample sense disambiguation.
• UKB: Graph Base WSD, is a collection of programs for performing graph-based Word Sense Disambiguation and lexical similarity/relatedness using a pre-existing Lexical Knowledge Base (LKB).

See also[link]

• Ambiguity
• Lesk algorithm
• Lexical substitution
• Part-of-speech tagging
• Polysemy
• Semeval
• Syntactic ambiguity
• Word sense
• Word sense induction

Notes[link]

Works cited[link]

• Agirre, E.; Lopez de Lacalle, A.; Soroa, A. (2009) "Knowledge-based WSD on Specific Domains: Performing better than Generic Supervised WSD" Proc. of IJCAI http://www.ijcai.org/papers09/Papers/IJCAI09-251.pdf 
• Agirre, E.; M. Stevenson. 2006. Knowledge sources for WSD. In Word Sense Disambiguation: Algorithms and Applications, E. Agirre and P. Edmonds, Eds. Springer, New York, NY.
• Bar-Hillel, Y. (1964). Language and information. Reading, MA: Addison-Wesley. 
• Buitelaar, P.; B. Magnini, C. Strapparava and P. Vossen. 2006. Domain-specific WSD. In Word Sense Disambiguation: Algorithms and Applications, E. Agirre and P. Edmonds, Eds. Springer, New York, NY.
• Chan, Y. S.; H. T. Ng. 2005. Scaling up word sense disambiguation via parallel texts. In Proceedings of the 20th National Conference on Artificial Intelligence (AAAI, Pittsburgh, PA).
• Edmonds, P. 2000. Designing a task for SENSEVAL-2. Tech. note. University of Brighton, Brighton. U.K.
• Fellbaum, Christiane (1997) "Analysis of a handwriting task" Proc. of ANLP-97 Workshop on Tagging Text with Lexical Semantics: Why, What, and How? Washington D.C., USA 
• Gliozzo, A.; B. Magnini and C. Strapparava. 2004. Unsupervised domain relevance estimation for word sense disambiguation. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP, Barcelona, Spain).
• Ide, N.; T. Erjavec, D. Tufis. 2002. Sense discrimination with parallel corpora. In Proceedings of ACL Workshop on Word Sense Disambiguation: Recent Successes and Future Directions (Philadelphia, PA).
• Kilgarriff, A. 1997. I don't believe in word senses. Comput. Human. 31(2), pp. 91–113.
• Kilgarriff, A.; G. Grefenstette. 2003. Introduction to the special issue on the Web as corpus. Computational Linguistics 29(3), pp. 333–347
• Kilgarriff, Adam; Joseph Rosenzweig, English Senseval: Report and Results May–June, 2000, University of Brighton
• Lapata, M.; and F. Keller. 2007. An information retrieval approach to sense ranking. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL, Rochester, NY).
• Lenat, D. "Computers versus Common Sense". http://www.youtube.com/watch?v=KSrUHGaUE_c. Retrieved 2008-12-10.  (GoogleTachTalks on YouTube)
• Lenat, D.; R. V. Guha. 1989. Building Large Knowledge-Based Systems, Addison-Wesley
• Lesk; M. 1986. Automatic sense disambiguation using machine readable dictionaries: How to tell a pine cone from an ice cream cone. In Proc. of SIGDOC-86: 5th International Conference on Systems Documentation, Toronto, Canada.
• Litkowski, K. C. 2005. Computational lexicons and dictionaries. In Encyclopaedia of Language and Linguistics (2nd ed.), K. R. Brown, Ed. Elsevier Publishers, Oxford, U.K.
• Magnini, B; G. Cavaglià. 2000. Integrating subject field codes into WordNet. In Proceedings of the 2nd Conference on Language Resources and Evaluation (LREC, Athens, Greece).
• McCarthy, D.; R. Koeling, J. Weeds, J. Carroll. 2007. Unsupervised acquisition of predominant word senses. Computational Linguistics 33(4): 553–590.
• McCarthy, D.; R. Navigli. 2009. The English Lexical Substitution Task, Language Resources and Evaluation, 43(2), Springer.
• Mihalcea, R. 2007. Using Wikipedia for Automatic Word Sense Disambiguation. In Proc. of the North American Chapter of the Association for Computational Linguistics (NAACL 2007), Rochester, April 2007.
• Mohammad, S; G. Hirst. 2006. Determining word sense dominance using a thesaurus. In Proceedings of the 11th Conference on European chapter of the Association for Computational Linguistics (EACL, Trento, Italy).
• Navigli, R. 2006. Meaningful Clustering of Senses Helps Boost Word Sense Disambiguation Performance. Proc. of the 44th Annual Meeting of the Association for Computational Linguistics joint with the 21st International Conference on Computational Linguistics (COLING-ACL 2006), Sydney, Australia.
• Navigli, R.; G. Crisafulli. Inducing Word Senses to Improve Web Search Result Clustering. Proc. of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP 2010), MIT Stata Center, Massachusetts, USA.
• Navigli, R.; M. Lapata. An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 32(4), IEEE Press, 2010.
• Navigli, R.; K. Litkowski, O. Hargraves. 2007. SemEval-2007 Task 07: Coarse-Grained English All-Words Task. Proc. of Semeval-2007 Workshop (SemEval), in the 45th Annual Meeting of the Association for Computational Linguistics (ACL 2007), Prague, Czech Republic.
• Navigli, R.;P. Velardi. 2005. Structural Semantic Interconnections: a Knowledge-Based Approach to Word Sense Disambiguation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 27(7).
• Palmer, M.; O. Babko-Malaya and H. T. Dang. 2004. Different sense granularities for different applications. In Proceedings of the 2nd Workshop on Scalable Natural Language Understanding Systems in HLT/NAACL (Boston, MA).
• Ponzetto, S. P.; R. Navigli. Knowledge-rich Word Sense Disambiguation rivaling supervised systems. In Proc. of the 48th Annual Meeting of the Association for Computational Linguistics (ACL), 2010.
• Pradhan, S.; E. Loper, D. Dligach, M. Palmer. 2007. SemEval-2007 Task 17: English lexical sample, SRL and all words. Proc. of Semeval-2007 Workshop (SEMEVAL), in the 45th Annual Meeting of the Association for Computational Linguistics (ACL 2007), Prague, Czech Republic.
• Schütze, H. 1998. Automatic word sense discrimination. Computational Linguistics, 24(1): 97–123.
• Snow, R.; S. Prakash, D. Jurafsky, A. Y. Ng. 2007. Learning to Merge Word Senses, Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL).
• Snyder, B.; M. Palmer. 2004. The English all-words task. In Proc. of the 3rd International Workshop on the Evaluation of Systems for the Semantic Analysis of Text (Senseval-3), Barcelona, Spain.
• Weaver, Warren (1949). "Translation". In Locke, W.N.; Booth, A.D.. Machine Translation of Languages: Fourteen Essays. Cambridge, MA: MIT Press. http://www.hutchinsweb.me.uk/MTNI-22-1999.pdf. 
• Wilks, Y.; B. Slator, L. Guthrie. 1996. Electric Words: dictionaries, computers and meanings. Cambridge, MA: MIT Press.
• Yarowsky, D. Word-sense disambiguation using statistical models of Roget's categories trained on large corpora. In Proc. of the 14th conference on Computational linguistics (COLING), 1992.
• Yarowsky, D. 1995. Unsupervised word sense disambiguation rivaling supervised methods. In Proc. of the 33rd Annual Meeting of the Association for Computational Linguistics.

External links and suggested reading[link]

Look up disambiguation in Wiktionary, the free dictionary.

• Computational Linguistics Special Issue on Word Sense Disambiguation (1998)
• Evaluation Exercises for Word Sense Disambiguation The de-facto standard benchmarks for WSD systems.
• Roberto Navigli. Word Sense Disambiguation: A Survey, ACM Computing Surveys, 41(2), 2009, pp. 1–69. An up-to-date state of the art of the field.
• Word Sense Disambiguation as defined in Scholarpedia
• Word Sense Disambiguation: The State of the Art (PDF) A comprehensive overview By Prof. Nancy Ide & Jean Véronis (1998).
• Word Sense Disambiguation Tutorial, by Rada Mihalcea and Ted Pedersen (2005).
• Word Sense Disambiguation: Algorithms and Applications, edited by Eneko Agirre and Philip Edmonds (2006), Springer. Covers the entire field with chapters contributed by leading researchers. www.wsdbook.org site of the book
• Bar-Hillel, Yehoshua. 1964. Language and Information. New York: Addison-Wesley.
• Edmonds, Philip & Adam Kilgarriff. 2002. Introduction to the special issue on evaluating word sense disambiguation systems. Journal of Natural Language Engineering, 8(4):279-291.
• Edmonds, Philip. 2005. Lexical disambiguation. The Elsevier Encyclopedia of Language and Linguistics, 2nd Ed., ed. by Keith Brown, 607-23. Oxford: Elsevier.
• Ide, Nancy & Jean Véronis. 1998. Word sense disambiguation: The state of the art. Computational Linguistics, 24(1):1-40.
• Jurafsky, Daniel & James H. Martin. 2000. Speech and Language Processing. New Jersey, USA: Prentice Hall.
• Litkowski, K. C. 2005. Computational lexicons and dictionaries. In Encyclopaedia of Language and Linguistics (2nd ed.), K. R. Brown, Ed. Elsevier Publishers, Oxford, U.K., 753–761.
• Manning, Christopher D. & Hinrich Schütze. 1999. Foundations of Statistical Natural Language Processing. Cambridge, MA: MIT Press. http://nlp.stanford.edu/fsnlp/
• Mihalcea, Rada. 2007. Word sense disambiguation. Encyclopedia of Machine Learning. Springer-Verlag.
• Resnik, Philip and David Yarowsky. 2000. Distinguishing systems and distinguishing senses: New evaluation methods for word sense disambiguation, Natural Language Engineering, 5(2):113-133. http://www.cs.jhu.edu/~yarowsky/pubs/nle00.ps
• Yarowsky, David. 2001. Word sense disambiguation. Handbook of Natural Language Processing, ed. by Dale et al., 629-654. New York: Marcel Dekker.

Ben Shneiderman
Born	(1947-08-21) August 21, 1947 (age 64) New York, NY
Residence	Bethesda, MD
Citizenship	United States
Nationality	American
Fields	Computer Science, Human-Computer Interaction, Information Visualization Social Media
Institutions	University of Maryland, College Park
Alma mater	State University of New York at Stony Brook
Doctoral advisor	Jack Heller
Doctoral students	Chris North, Andrew Sears, Eser Kandogan, Adam Perer, Harry Hochheiser, Haixia Zhao, David Wang
Known for	Nassi–Shneiderman diagram, treemap, Information Visualization
Notable awards	Member National Academy of Engineering, ACM Fellow, AAAS Fellow, IEEE Fellow, SIGCHI LifeTime Achievement, Miles Conrad Award

Ben Shneiderman (born August 21, 1947) is an American computer scientist, and professor for Computer Science at the University of Maryland Human-Computer Interaction Lab at the University of Maryland, College Park. He conducted fundamental research in the field of human–computer interaction, developing new ideas, methods, and tools such as the direct manipulation interface, and his eight rules of design.^[1]

Biography[link]

He is a graduate of the Bronx High School of Science, and received a B.S. in Mathematics and Physics from the City College of New York in 1968, and then went on to study at the State University of New York at Stony Brook, where he received an M.S. in Computer Science in 1972 and graduated with a Ph.D. in 1973.

He was inducted as a Fellow of the Association for Computing Machinery in 1997, a Fellow of the American Association for the Advancement of Science in 2001, a Member of the National Academy of Engineering in 2010, and an IEEE Fellow in 2012.^[2]

In 2002 his book Leonardo's Laptop: Human Needs and the New Computing Technologies was Winner of a IEEE-USA Award for Distinguished Contributions Furthering Public Understanding of the Profession.

He also received Honorary Doctorates by the University of Guelph (Canada) and by the University of Castile-La Mancha (Spain).

Work[link]

In his earlier work on studying programmers, he conducted experiments which suggested that flowcharts were not helpful for writing, understanding, or modifying computer programs. He developed the prinicples of Direct manipulation interface design in 1982, and applied this to develop the user interface for highlighted phrases in text, that became the hot link of the Web.

His major work in recent years has been on information visualization, originating the treemap concept for hierarchical data. He also developed dynamic queries sliders with multiple coordinated displays that are a key component of Spotfire, which was acquired by TIBCO in 2007. His work continued on visual analysis tools for time series data, TimeSearcher, high dimensional data, Hierarchical Clustering Explorer, and social network data, SocialAction ^[3] plus NodeXL. Current work deals with visualization of temporal event sequences, such as found in Electronic Health Records, in systems such as LifeLines2.^[4]

In addition to his influential work in user interface design, he is known for the co-invention (together with Isaac Nassi) of the Nassi–Shneiderman diagrams, a graphical representation of the design of structured software.

He also defined the research area of universal usability to encourage greater attention to diverse users, languages, cultures, screen sizes, network speeds, and technology platforms.

Publications[link]

A selection:

• 1980. Software Psychology: Human Factors in Computer and Information Systems; Little, Brown and Co. ISBN 0-87626-816-5
• 1987. Designing the User Interface: Strategies for Effective Human-Computer Interaction, 1st edition. Addison-Wesley. ISBN 0-321-26978-0.'
• 1999. Readings in Information Visualization: Using Vision to Think. With Stuart K. Card and Jock D. Mackinlay. Morgan Kaufmann. ISBN 1-55860-533-9.
• 2002. Leonardo's Laptop: Human Needs and the New Computing Technologies; MIT Press. ISBN 0-262-69299-6.
• 2010. Designing the User Interface: Strategies for Effective Human-Computer Interaction, 5th edition. With C. Plaisant. Addison-Wesley. ISBN 0-321-26978-0.'
• 2011. Analyzing Social Media Networks with NodeXL: Insights from a Connected World. With D. Hansen and M. Smith. Morgan Kaufmann. ISBN 978-0-12-382229-1.

References[link]

External links[link]

• Ben Shneiderman's home page
• Ben Shneiderman's Collection of Historical Videos on YouTube
• A short history of structured flowcharts (Nassi–Shneiderman diagram)
• NodeXL free download, for social media network analysis and visualization
• Ben Shneiderman's CV, with an extensive list of publications.
• Experimental investigations of the utility of detailed flowcharts in programming, B. Shneiderman, R. Mayer, D. McKay, and P. Heller, Communications of the ACM, Vol. 20, Iss. 6, June 1977.

Rick Astley
Astley performing in Santiago de Chile, in 2009.
Background information
Birth name	Richard Paul Astley
Born	(1966-02-06) 6 February 1966 (age 46) Newton-le-Willows, Lancashire, England
Genres	Pop, dance-pop, blue-eyed soul
Occupations	Singer-songwriter, musician
Instruments	Vocals, guitar, drums, keyboards
Years active	1985–1993 2000–present
Labels	RCA, Polydor, Cruz
Associated acts	FBI Stock Aitken Waterman
Website	rickastley.co.uk

Richard Paul "Rick" Astley ( /ˈrɪk ˈæstli/; born 6 February 1966) is an English singer-songwriter, musician, and radio personality. He is known for his 1987 song, "Never Gonna Give You Up", which was a #1 hit single in 25 countries.^[1] Astley holds the record for being the only male solo artist to have his first 8 singles reach the Top 10 in the UK^[2] and by retirement in 1993 had sold approximately 40 million records worldwide.^[3][4][5]

After retiring from the music industry in 1993, Astley made a comeback in 2007 when he became an Internet phenomenon, as his video for "Never Gonna Give You Up" became part of a popular Internet meme known as "Rickrolling".^[6] Astley was voted "Best Act Ever" by Internet users at the MTV Europe Music Awards 2008.^[7]

Early life[link]

Richard Paul Astley was born on 6 February 1966 in Newton-le-Willows, Lancashire, England, becoming the fourth child of his family. His parents divorced when he was five, and Astley was brought up by his father.^[8] His musical career started when he was ten, singing in the local church choir.^[9] During his schooldays, Astley formed and played the drums in a number of local bands, where he met guitarist David Morris.^[2][10] After leaving school at sixteen, Astley was employed during the day as a driver in his father's market-gardening business and played drums on the Northern club circuit at night in bands such as “Give Way” - specialising in covering Beatles and Shadows songs - and “FBI”, which won several local talent competitions.^[9]

Signing to Stock Aitken Waterman[link]

In 1985, Astley was performing as a drummer with a soul band named FBI, with Morris on guitar. They were a well known local band writing and performing their own music, gigging in pubs and clubs. When FBI's lead singer left the band, and Morris left to concentrate on his career in hairdressing,^[10] Astley offered to be the lead vocalist. This was when he was noticed by the record producer Pete Waterman, who persuaded him to come to London to work at the PWL recording studio,^[2] with RCA Records publishing his records. Under the tutelage of the production team of Mike Stock, Matt Aitken and Pete Waterman, known as Stock Aitken Waterman, Astley was taught about the recording process and groomed for his future career, supposedly starting off as the recording studio 'tea boy'.^[11] The reason for Astley to be hired initially as a 'tape op', was to overcome his shyness.^[12] SAW also hired most of FBI, including Morris as a guitarist/songwriter.^[10]

Success[link]

His first single was the little-known "When You Gonna", released as a collaboration with Lisa Carter, with little promotion. It did not chart. His first solo offering was "Never Gonna Give You Up", recorded on New Year's Day 1987, and released eight months later, in August. Astley's distinctive rich, deep voice combined with dance pop, made the song an immediate success,^[13] spending five weeks at the top of the British charts and becoming the year's highest-selling single. The song was also a worldwide number one hit, topping the charts in 24 other countries, including the U.S., Australia, and Germany. It would become the first of 13 (worldwide) top 30 hit singles for him. "Never Gonna Give You Up" won Best British single at the 1988 BPI awards (now called the BRIT Awards),^[14] and he performed the hit in front of a global audience of 100 million.^[2][15]

His next single was "Whenever You Need Somebody", which was released in October. The single was a recycled Stock, Aitken, Waterman song, originally recorded by O'Chi Brown in 1985. It became a successful European hit, reaching #1 in seven countries, including Germany and Sweden, following up the success of his debut single. It also reached #3 in the UK. It was not released in North America.^[16]

In November 1987, the album Whenever You Need Somebody, containing four Astley-written tracks, also reached number one in the UK and Australia, and #10 in the U.S. It was certified 4x Platinum in the UK and Canada, and 2x Platinum in the US. Overall Whenever You Need Somebody sold 15.2 million copies worldwide, making him the top selling British act of the year.^[2]

In the run up to Christmas 1987, Astley released a cover version of the Nat King Cole classic "When I Fall in Love". This single is mainly remembered for a closely fought contest for UK Christmas Number 1. Rivals EMI, hoping to see their act the Pet Shop Boys reach #1, re-released the version by Nat King Cole.^[17][18] This led to a slowdown of purchases of Astley's version, allowing the Pet Shop Boys to reach the coveted top spot. Despite selling over 200,000 copies and gaining a Silver certification from the BPI,^[19] it peaked in the UK at #2 for two weeks. The re-release of Nat King Cole's version reached #4. The B side was a dance number "My Arms Keep Missing You", which was successful in mainland Europe.

Astley's fourth single release would be "Together Forever" in 1988, reaching #2 in the UK. It was denied the top spot by Neighbours sensation Kylie Minogue's debut "I Should Be So Lucky".^[20] "Together Forever" was more successful state-side, topping the U.S charts, making it his second U.S chart topper, which meant Astley was one of the few British acts to crack the American market. In 1989 he was nominated for a Grammy Award for Best New Artist, but lost to Tracy Chapman.

His fifth and final release from his debut album was "It Would Take a Strong Strong Man". It was a more soulful song, when compared to his other releases, and was mainly intended for the North American market. Thus, it was not released in Britain. It was another hit for Astley, reaching #10 on the U.S Billboard Hot 100, and #1 in Canada. During the period between his debut release and his fifth single, Astley outsold every other artist in the world.^[21] In the UK, he was in the Top 40 every week for the first 6 months of his career.^[2]

A fire in the PWL studios destroyed much of Astley's new material,^[2] causing a delay in the release of his second album. Hold Me In Your Arms was eventually released in January 1989, containing five singles, and reached #8 in the UK and #19 in the US, being certified platinum in the UK and gold in the US.

Astley's relationship with British media deteriorated significantly after the release of Whenever You Need Somebody, with the media calling him a 'puppet' of Stock Aitken Waterman.^[14] This was despite Astley writing five of his new album's tracks. The negative press inevitably affected the sales of his singles.^[22] The first single from the album to be released was "She Wants To Dance With Me", a number penned by Astley himself. It was another successful single, reaching #6 on both the UK and US charts. "Take Me to Your Heart" was the next single to be released from the album. It reached #8 in the UK and was not released in the US. The Astley-written ballad "Hold Me in Your Arms" reached #10 in the UK and was also not released in North America. The next two singles released from the album were intended for the North American market. "Giving Up On Love" and a cover of The Temptations song "Ain't Too Proud To Beg" charted at #38 and #89 in the US respectively.

In December 1989, Astley set off on his first world tour, touring 15 countries including the UK, US, Australia, and Japan.^[2] By the end of the tour, Astley was tiring of the negative press, and wanted to explore alternative paths as a musician. Thus, he left his producers Stock Aitken Waterman, with RCA records buying out his contract with PWL.

Switching to soul and AC[link]

By 1990, Astley had parted company with Stock, Aitken, and Waterman. He also decided to leave his dance-pop days behind him, moving towards his passion, soul. This shift in musical genre led him to change his image too, ditching the boy next door look, presenting himself as a mature and passionate musician. His third album, Free, was released in 1991 containing collaborations with Elton John.^[14] The album contained three singles, and reached #9 in the UK and #31 in the US.

He achieved one more major success with the 1991 ballad "Cry for Help", which reached #7 in both the UK and the US. This would place Astley in The Guinness Book of Records, as he became the first male solo artist to have his first eight singles all chart in the UK Top 10. This record still stands to this day.^[2] The other two singles from Free were not as successful. "Move Right Out" reached #58 in the UK and #81 in the US; and "Never Knew Love" reached #70 in the UK and did not chart in the US. Free would mark the end of Astley's successful period, and "Cry for Help" would be the last Astley single to make the Top 10 in either the UK or US (as of May 2010).

His next album, Body and Soul, was released in 1993, and was largely an Adult Contemporary album. By the time the album was released, Astley had decided to retire from the music industry. As a result, the album did not get a lot of promotion,^[2] not charting in the UK but managing to make the Billboard 200, peaking at #182. The two singles, "The Ones You Love" and "Hopelessly", performed very well on the US adult contemporary chart, peaking at #19 and #4 respectively. "The Ones You Love" peaked at #48 in the UK but did not chart in the US. "Hopelessly" also crossed over and peaked at #28 on the US Billboard 100, staying in the US top 40 for five weeks, and #33 in the UK. It was named as one of the most performed songs at the 1994 BMI Awards,^[23] and is one of the few songs to achieve BMI 'Million-Air' status.^[24]

Retirement[link]

After 1993, Astley decided to retire from the music industry at the young age of 27, deciding that family life was more important. During Astley's time out of the music business, he raised his daughter Emilie, born in 1992. Thus, for much of the 1990s and early 2000s, Astley remained largely out of the spotlight. One notable musical appearance by Astley during retirement was as a backing singer on The Lion King soundtrack in 1994.^[11]

Return to singing[link]

Almost 10 years after Body and Soul, Astley finally returned to the music world, signing a co-publishing deal with Polydor and releasing Keep It Turned On in 2002. The album featured the single "Sleeping", which became a minor club hit, thanks to a set of remixes from U.S. house producer Todd Terry. Keep It Turned On was only released in Continental Europe.^[2]

Astley's first compilation album, Greatest Hits, was released in 2002, and reached #16 on the UK Albums Chart. With no promotion from Astley, it sold over 100,000 copies and was certified Gold by the BPI.^[2] After retirement in 1993, Astley continued to write songs for various acts and in 2003 he managed to chart at #10 in the UK as a songwriter with "Shakespeare's (Way With) Words" performed by short-lived boy band One True Voice.

In 2004, Astley toured for the first time in 14 years, which led him to a record contract with Sony BMG.^[2] In March 2005, Astley released the album Portrait in which he covered many classic standards such as "Vincent",^[25] "Nature Boy" and "Close to You". Both Astley and Sony BMG were unhappy with the end result so the album was poorly promoted,^[2] yet managed to reach #26 on the UK Albums Chart.

Astley performing in Denmark '09

In April 2008, the album "The Ultimate Collection: Rick Astley" was released by Sony BMG and by early May it had reached #17 on the UK Top 40 Albums Chart,^[26] again with no promotion from Astley.

In September 2008, Rick was nominated for the 'Best Act Ever' award at the MTV Europe Music Awards^[7] The push to make Astley the winner of the award continued after the announcement, as well as efforts to encourage MTV to personally invite Astley to the awards ceremony.^[27] On 7 November, following a massive internet campaign by fans, Rick won the award in Liverpool, but was not there in person to receive it. Perez Hilton collected the prize on his behalf.^[28] On the back of this, "Never Gonna Give You Up" returned to the UK charts, over 21 years after it was released, peaking at #73 during the Christmas period.

During the late 2000s, Astley continued touring across the globe, touring with various other '80s acts, such as Boy George and Belinda Carlisle, in the Here and Now Tour.^[2] In April 2009, he wrote an article for Time about moot.^[29]

Astley today[link]

Astley was a special guest throughout Peter Kay's new tour, The Tour That Doesn't Tour Tour...Now On Tour, from 27 April to 22 May 2010. To mark the occasion, Rick Astley released a new single "Lights Out" on his own label. It was released on 7 June 2010.^[30] This was Astley's first release in the UK Singles Chart in 17 years. It was well received by radio, peaking #15 on the UK Airplay Charts, but failed to become a commercial hit, reaching only #97 on the UK Singles Chart.

During the summer 2010, Astley became a radio DJ for London's Magic FM, presenting a Sunday show.^[31][32] Initially the contract was 8 weeks but he proved popular with listeners and his contract was extended till the end of the year.^[33] In December 2010, Astley co-hosted the Chris Evans Breakfast Show on BBC Radio 2 with Peter Kay,^[34] and in March 2011 appeared in Comic Relief's Red Nose Day telethon on the BBC.^[35][36]

Personal life[link]

Rick Astley is married to Lene Bausager, and the couple have one daughter, Emilie, who was born in 1992. Astley met Lene when she was working as a promoter with RCA in 1988.^[8] Lene is a film producer, and was nominated for the 2006 Academy Award for Best Live Action Short Film for the Sean Ellis film Cashback, where she was the main producer.^[37][38] The family lives in the London suburb of Richmond.^[39]

Discography[link]

Canada Top data: for singles and albums from The Record magazine. US Top data: for singles from The Billboard Hot 100, for albums from The Billboard 200; UK Top data for singles and albums is from UK Singles Chart. Based on various music charts in the UK, US and Canada, Astley has charted a grand total of 14 different hit singles and 6 different hit albums, as of April 2010.

Studio albums[link]

• Whenever You Need Somebody (1987)
• Hold Me in Your Arms (1989)
• Free (1991)
• Body & Soul (1993)
• Keep It Turned On (2001)
• Portrait (2005)

Rickroll internet phenomenon[link]

Astley rickrolling the Macy's Thanksgiving Day Parade, 2008

In 2007,^[40] Rick Astley became the subject of a viral internet meme known as Rickrolling. This is where internet users are tricked into watching Rick Astley's video "Never Gonna Give You Up" by following a link that claims to be something else.^[41] Views of this video on various websites are now in the millions. The phenomenon became so popular that on 1 April 2008, YouTube pranked its users by making every single featured video on its front page a Rickroll.^[42]

On November 27, 2008, Astley himself participated in a live Rickroll during the Macy's Thanksgiving Day Parade while the Foster's Home for Imaginary Friends characters were singing "Best Friend", the theme from the 1970s TV series The Courtship of Eddie's Father. Midway through the song, Astley emerged from the float and began to lip sync his signature hit. At the end of Astley's performance, Cheese (a character from Foster's) shouted out "I like Rickrolling!".^[43][44]

Despite the video garnering millions of hits on YouTube, Astley has earned almost no money from the meme, receiving only US$12 in royalties from YouTube for his performance share.^[45]

See also[link]

• List of artists who reached number one on the Hot 100 (U.S.)
• List of artists who reached number one on the U.S. Dance chart
• List of Number 1 Dance Hits (United States)
• List of number-one albums (UK)
• List of number-one singles (UK)
• List of number-one hits (United States)
• List of songs by British artists which reached number-one on the Hot 100 (USA)
• The Rickrollerz

References[link]

External links[link]

Wikimedia Commons has media related to: Rick Astley

Wikiquote has a collection of quotations related to: Rick Astley

• Official Rick Astley website
• Official Rick Astley MySpace
• Official Rick Astley YouTube channel (1987-93) (country restricted)
• Official Rick Astley YouTube channel (2010-)^{[dubious – discuss]}