Search for: All records | NSF Public Access

What’s in a Name? Answer Equivalence For Open-Domain Question Answering

Chenglei Si, Chen Zhao ( January 2021 , Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing)

A flaw in QA evaluation is that annotations often only provide one gold answer. Thus, model predictions semantically equivalent to the answer but superficially different are considered incorrect. This work explores mining alias entities from knowledge bases and using them as additional gold answers (i.e., equivalent answers). We incorporate answers for two settings: evaluation with additional answers and model training with equivalent answers. We analyse three QA benchmarks: Natural Questions, TriviaQA and SQuAD. Answer expansion increases the exact match score on all datasets for evaluation, while incorporating it helps model training over real-world datasets. We ensure the additional answers are valid through a human post hoc evaluation.

Full Text Available