Stanford AI Lab Showcases Research at EMNLP and CoNLL 2021
The Stanford Artificial Intelligence Laboratory (SAIL) has announced its accepted papers for the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) and the Conference on Computational Natural Language Learning (CoNLL). The announcement highlights six key research contributions from Stanford faculty and students, covering diverse areas within natural language processing. Topics include robust communication-based training for pragmatic speakers, cross-domain data integration for biomedical named entity disambiguation, and a new dataset for document-level natural language inference in legal contracts. Other featured works explore the emergence of shape bias through communicative efficiency, unsupervised grammatical error correction using language models, and sensitivity as a complexity measure for sequence classification. The laboratory provides direct links to academic papers, video presentations, and project websites, encouraging further engagement with the researchers. This collection underscores Stanford's ongoing contribution to advancing NLP methodologies, particularly in specialized domains like law and biomedicine, as well as fundamental theories of language acquisition and model evaluation.
Wire timeline
Stanford AI Lab Showcases Research at EMNLP and CoNLL 2021
The Stanford Artificial Intelligence Laboratory (SAIL) has announced its accepted papers for the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) and the Conference on Computational Natural Language Learning (CoNLL). The announcement highlights six key research contributions from Stanford faculty and students, covering diverse areas within natural language processing. Topics include robust communication-based training for pragmatic speakers, cross-domain data integration for biomedical named entity disambiguation, and a new dataset for document-level natural language inference in legal contracts. Other featured works explore the emergence of shape bias through communicative efficiency, unsupervised grammatical error correction using language models, and sensitivity as a complexity measure for sequence classification. The laboratory provides direct links to academic papers, video presentations, and project websites, encouraging further engagement with the researchers. This collection underscores Stanford's ongoing contribution to advancing NLP methodologies, particularly in specialized domains like law and biomedicine, as well as fundamental theories of language acquisition and model evaluation.
The Stanford AI Lab Blog