pkavumba/balanced-copa

Tasks

• question-answering

Citation text from the card

@inproceedings{kavumba-etal-2019-choosing,
    title = "When Choosing Plausible Alternatives, Clever Hans can be Clever",
    author = "Kavumba, Pride  and
      Inoue, Naoya  and
      Heinzerling, Benjamin  and
      Singh, Keshav  and
      Reisert, Paul  and
      Inui, Kentaro",
    booktitle = "Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/D19-6004",
    doi = "10.18653/v1/D19-6004",
    pages = "33--42",
    abstract = "Pretrained language models, such as BERT and RoBERTa, have shown large improvements in the commonsense reasoning benchmark COPA. However, recent work found that many improvements in benchmarks of natural language understanding are not due to models learning the task, but due to their increasing ability to exploit superficial cues, such as tokens that occur more often in the correct answer than the wrong one. Are BERT{'}s and RoBERTa{'}s good performance on COPA also caused by this? We find superficial cues in COPA, as well as evidence that BERT exploits these cues.To remedy this problem, we introduce Balanced COPA, an extension of COPA that does not suffer from easy-to-exploit single token cues. We analyze BERT{'}s and RoBERTa{'}s performance on original and Balanced COPA, finding that BERT relies on superficial cues when they are present, but 

All datasets marked Unclear | JSON