25 citations · 67 across the 43 of their papers we have counts for
6 papers · 1 filter
Coreference Reasoning in Machine Reading Comprehension
Mingzhu Wu, Nafise Sadat Moosavi, Dan Roth +1
Coreference resolution is essential for natural language understanding and has been long studied in NLP. In recent years, as the format of Question Answering (QA) became a standard…
Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution
Juntao Yu, Nafise Sadat Moosavi, Silviu Paun +1
Now that the performance of coreference resolvers on the simpler forms of anaphoric reference has greatly improved, more attention is devoted to more complex aspects of anaphora. O…
Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures
Nafise Sadat Moosavi, Marcel de Boer, Prasetya Ajie Utama +1
Existing NLP datasets contain various biases, and models tend to quickly learn those biases, which in turn limits their robustness. Existing approaches to improve robustness agains…
Towards Debiasing NLU Models from Unknown Biases
Prasetya Ajie Utama, Nafise Sadat Moosavi, Iryna Gurevych
NLU models often exploit biases to achieve high dataset-specific performance without properly learning the intended task. Recently proposed debiasing methods are shown to be effect…
Improving QA Generalization by Concurrent Modeling of Multiple Biases
Mingzhu Wu, Nafise Sadat Moosavi, Andreas Rücklé +1
Existing NLP datasets contain various biases that models can easily exploit to achieve high performances on the corresponding evaluation sets. However, focusing on dataset-specific…
Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance
Prasetya Ajie Utama, Nafise Sadat Moosavi, Iryna Gurevych
Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distrib…