Speaker: Tristan Miller, Technische Universität Darmstadt (Germany) Abstract: Word sense disambiguation (WSD) – the task of determining which meaning a word carries in a particular context – is a core research problem in computational linguistics. Though it has long been recognized that supervised (i.e., machine learning–based) approaches to WSD can yield impressive results, they require an amount of manually annotated training data that is often too expensive or impractical to obtain. This is a particular problem for under-resourced languages and text domains, and is also a hurdle in well-resourced languages when processing the sort of lexical-semantic anomalies employed for deliberate effect in humour and wordplay. In contrast to supervised systems are knowledge-based techniques, which rely only on pre-existing lexical-semantic resources (LSRs) such as dictionaries and thesauri. These techniques are of more general applicability but tend to suffer from lower performance due to the informational gap between the target word's context and the sense descriptions provided by the LSR. In this seminar, we treat the task of extending the efficacy and applicability of knowledge-based WSD, both generally and for the particular case of English puns. In the first part of the talk, we present two approaches for bridging the information gap and thereby improving WSD coverage and accuracy. In the first approach, we supplement the word's context and the LSR's sense descriptions with entries from a distributional thesaurus. The second approach enriches an LSR's sense information by aligning it to other, complementary LSRs. In the second part of the talk, we describe how these techniques, along with evaluation methodologies from traditional WSD, can be adapted for the "disambiguation" of puns, or rather for the automatic identification of their double meanings.

• published: 31 May 2017
• views: 457