AutoEQA: Auto-Encoding Questions for Extractive Question Answering

Stalin Varanasi; Saadullah Amin; Günter Neumann

In: The 2021 Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing (EMNLP-2021), Findings of EMNLP, November 7-11, Punta Cana, Dominican Republic, The Association for Computational Linguistics, 209 N. Eighth Street Stroudsburg, PA 18360 USA, 11/2021.


There has been a significant progress in the field of extractive question answering (EQA) in the recent years. However, most of them rely on annotations of answer-spans in the corresponding passages. In this work, we address the problem of EQA when no annotations are present for the answer span, i.e., when the dataset contains only questions and corresponding passages. Our method is based on auto-encoding of the question that performs a question answering (QA) task during encoding and a question generation (QG) task during decoding. Our method performs well in a zero-shot setting and can provide an additional loss to boost performance for EQA.


4492_Paper.pdf (pdf, 430 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence