NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering

Tengxun Zhang, Hongfei Xu, Josef van Genabith, Deyi Xiong, Hongying ZAN

Keywords: Tabular-Textual Question Answering, Non-Autoregressive Program Generation, Natural Language Processing

TL;DR: We present a non-autoregressive program generation model for the numerical reasoning of hybrid question answering to address the exposure bias issue of autoregressive generation and to boost the decoding speed.

Abstract: Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous information, and the types of reasoning are mainly divided into numerical reasoning and span extraction. The current numerical reasoning method uses LSTM to autoregressively decode program sequences, and each decoding step produces either an operator or an operand. However, the step-by-step decoding suffers from exposure bias, and the accuracy of program generation drops sharply with progressive decoding. In this paper, we propose a non-autoregressive program generation framework, which facilitates program generation in parallel. Our framework, which independently generates complete program tuples containing both operators and operands, can significantly boost the speed of program generation while addressing the error accumulation issue. Our experiments on the MultiHiertt dataset shows that our model can bring about large improvements (+7.97 EM and +6.38 F1 points) over the strong baseline, establishing the new state-of-the-art performance, while being much faster (~21x) in program generation. The performance drop of our method is also significantly smaller than the baseline with increasing numbers of numerical reasoning steps.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)