Context-Aware Answer Extraction in Question Answering

Extractive QA models have shown very promising performance in predicting the correct answer to a question for a given passage. However, they sometimes result in predicting the correct answer text but in a context irrelevant to the given question. This discrepancy becomes especially important as the number of occurrences of the answer text in a passage increases. To resolve this issue, we propose \textbf{BLANC} (\textbf{BL}ock \textbf{A}ttentio\textbf{N} for \textbf{C}ontext prediction) based on two main ideas: context prediction as an auxiliary task in multi-task learning manner, and a block attention method that learns the context prediction task. With experiments on reading comprehension, we show that BLANC outperforms the state-of-the-art QA models, and the performance gap increases as the number of answer text occurrences increases. We also conduct an experiment of training the models using SQuAD and predicting the supporting facts on HotpotQA and show that BLANC outperforms all baseline models in this zero-shot setting.

[1]  Eunsol Choi,et al.  MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension , 2019, MRQA@EMNLP.

[2]  Philip Bachman,et al.  NewsQA: A Machine Comprehension Dataset , 2016, Rep4NLP@ACL.

[3]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[4]  Wei Zhang,et al.  Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering , 2017, ICLR.

[5]  Hannaneh Hajishirzi,et al.  Multi-hop Reading Comprehension through Question Decomposition and Rescoring , 2019, ACL.

[6]  Jian Su,et al.  Densely Connected Attention Propagation for Reading Comprehension , 2018, NeurIPS.

[7]  Richard Socher,et al.  Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering , 2019, ICLR.

[8]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[9]  Ali Farhadi,et al.  Bidirectional Attention Flow for Machine Comprehension , 2016, ICLR.

[10]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[11]  Ming-Wei Chang,et al.  Latent Retrieval for Weakly Supervised Open Domain Question Answering , 2019, ACL.

[12]  Danqi Chen,et al.  A Discrete Hard EM Approach for Weakly Supervised Question Answering , 2019, EMNLP.

[13]  Ankur P. Parikh,et al.  Multi-Mention Learning for Reading Comprehension with Neural Cascades , 2017, ICLR.

[14]  Eunsol Choi,et al.  Coarse-to-Fine Question Answering for Long Documents , 2016, ACL.

[15]  Danqi Chen,et al.  A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task , 2016, ACL.

[16]  Ming-Wei Chang,et al.  Natural Questions: A Benchmark for Question Answering Research , 2019, TACL.

[17]  Omer Levy,et al.  SpanBERT: Improving Pre-training by Representing and Predicting Spans , 2019, TACL.

[18]  Rajarshi Das,et al.  Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering , 2019, ICLR.

[19]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[20]  Kevin Gimpel,et al.  ALBERT: A Lite BERT for Self-supervised Learning of Language Representations , 2019, ICLR.

[21]  Jason Weston,et al.  Reading Wikipedia to Answer Open-Domain Questions , 2017, ACL.

[22]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[23]  Wei Li,et al.  A Unified Model for Document-Based Question Answering Based on Human-Like Reading Strategy , 2018, AAAI.

[24]  Minlie Huang,et al.  A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction , 2020, ACL.