Overview
The Conference on Empirical Methods in Natural Language Processing (EMNLP) will be held online and in Punta Cana, Dominican Republic.
Amazon organizing committee members
-
Amazon Visiting Academic
Area Chair, NLP Applications -
Amazon Visiting Academic
Area Chair, Machine Learning for NLP -
Area Chair, Information Extraction
-
Area Chair, Machine Learning for NLP
-
Virtual Infrastructure Chair
-
Area Chair, Machine Translation and Multilinguality
-
Simone FiliceArea Chair, Information Retrieval and Text Mining
-
Area Chair, Machine Translation and Multilinguality
-
Area Chair, Machine Translation and Multilinguality
-
Senior Area Chair, Multidisciplinary and AC COI
-
Area Chair, Information Extraction
-
Area Chair, Dialogue and Interactive Systems
-
Area Chair, Efficient Methods for NLP
-
Senior Area Chair, Dialogue and Interactive Systems
-
Area Chair, Information Retrieval and Text Mining
-
Aston ZhangArea Chair, NLP Applications
-
Area Chair, Semantics: Lexical, Sentence level, Textual Inference and Other Areas
Accepted publications
-
EMNLP 2021, ICLR 2021 Workshop on Weakly Supervised Learning2021
Workshops
EMNLP 2021 Workshop on Simple and Efficient Natural Language Processing (SustaiNLP)
November 10
The Natural Language Processing (NLP) community has, in recent years, demonstrated a notable focus on improving higher scores on standard benchmarks and taking the lead on community-wide leaderboards (e.g., GLUE, SentEval). While this aspiration has led to improvements in benchmark performance of (predominantly neural) models, it has also resulted in a worrysome increase in model complexity and the amount of computational resources required for training and using the current state-of-the-art models. Moreover, the recent research efforts have, for the most part, failed to identify sources of empirical gains in models, often failing to empirically justify the model complexity beyond benchmark performance.
EMNLP 2021 Workshop on NLP for Conversational AI
November 10
Amazon organizers: Alexandros Papangelis, Seokhwan Kim, Behnam Hedayatnia, Dilek Hakkani-Tür, Ming Sun
Website: https://sites.google.com/view/3rdnlp4convai/
Website: https://sites.google.com/view/3rdnlp4convai/
EMNLP 2021 Workshop on Fact Extraction and VERification (FEVER)
November 10 - November 11
EMNLP 2021 Workshop on Insights from Negative Results in NLP
November 10
Amazon organizers: Anna Rumshisky, Markus Mueller
Website: https://insights-workshop.github.io/2021/people/
Website: https://insights-workshop.github.io/2021/people/
EMNLP 2021 Workshop on the Fifth Widening NLP (WiNLP)
November 11
Amazon organizers: Kai-Wei Chang (Amazon visiting academic, Dan Roth (Amazon Scholar),
Website: http://www.winlp.org/winlp-2021-workshop/
Website: http://www.winlp.org/winlp-2021-workshop/
EMNLP 2021 Workshop on Evaluations and Assessments of Neural Conversation Systems (EANCS)
November 11
Amazon organizers: Dilek Hakkani-Tur, Lihong Li, Haoming Jiang
Website: https://sites.google.com/view/eancs
Website: https://sites.google.com/view/eancs
Tutorials
Robustness and Adversarial Examples in Natural Language Processing
November 10
Amazon speakers: Kai-Wei Chang (Amazon Visiting Academic), He He (Amazon Visiting Academic)
Knowledge-Enriched Natural Language Generation
November 10
Amazon speaker: Heng Ji (Amazon Scholar)
November 05, 2021
Natural-language understanding and question answering are areas of focus, with additional topics ranging from self-learning to text summarization.
Related content
-
December 06, 2023Research on natural-language understanding seeks to harness the power of large language models, while query reformulation and text summarization emerge as topics of particular interest.
-
January 18, 2023On natural-language-understanding tasks, student models trained only on task-specific data outperform those trained on a mix that includes generic data.
-
December 14, 2022EMNLP papers examine constrained generation of rewrite candidates and automatic selection of information-rich training data.
-
December 13, 2022Amazon Machine Learning Fellow Jiao Sun works on strategies to control text generation.