Members of the Department of Computational Linguistics had 6 papers accepted to the main conference of The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021):
- Contrastive Conditioning for Assessing Disambiguation in MT: A Case Study of Distilled Bias. ; (2021).
- Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models. ; ; (2021).
- Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT. ; ; (2021).
- Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution.; (2021).
- Sparse Attention with Linear Units.; ; (2021).
- (2021). Revisiting the Uniform Information Density Hypothesis.
a 7th paper has been accepted to the Findings of EMNLP: