Using Question Answering Rewards to Improve Abstractive Summarization

Neural abstractive summarization models have drastically improved in the recent years. However, the summaries generated by these models generally suffer from issues such as: not cap-turing the critical facts in source documents, and containing facts that are inconsistent with the source documents. In this work, we present a general framework to train abstractive summarization models to alleviate such issues. We first train a sequence-to-sequence model to summarize documents, and then further train this model in a Reinforcement Learning set-ting with question-answering based rewards. We evaluate the summaries generated by the this framework using multiple automatic measures and human judgements. The experimen-tal results show that the question-answering rewards can be used as a general framework to improve neural abstractive summarization. Particularly, the results from human evaluations show that the summaries generated by our approach are preferred over 30% of the time over the summaries generated by general abstractive summarization models.

[1]  Richard Socher,et al.  A Deep Reinforced Model for Abstractive Summarization , 2017, ICLR.

[2]  Richard Socher,et al.  Evaluating the Factual Consistency of Abstractive Text Summarization , 2019, EMNLP.

[3]  Mona T. Diab,et al.  FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization , 2020, ACL.

[4]  R'emi Louf,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.

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

[6]  Qingyang Wu,et al.  TextGAIL: Generative Adversarial Imitation Learning for Text Generation , 2020, AAAI.

[7]  Mirella Lapata,et al.  Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization , 2018, EMNLP.

[8]  Haoran Li,et al.  Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization , 2018, COLING.

[9]  Omer Levy,et al.  BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension , 2019, ACL.

[10]  Colin Raffel,et al.  Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer , 2019, J. Mach. Learn. Res..

[11]  Furu Wei,et al.  Faithful to the Original: Fact Aware Neural Abstractive Summarization , 2017, AAAI.

[12]  Percy Liang,et al.  Know What You Don’t Know: Unanswerable Questions for SQuAD , 2018, ACL.

[13]  Naren Ramakrishnan,et al.  Neural Abstractive Text Summarization with Sequence-to-Sequence Models , 2018, Trans. Data Sci..

[14]  D. Roth,et al.  Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary , 2020, Transactions of the Association for Computational Linguistics.

[15]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[16]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[17]  Sylvain Lamprier,et al.  QuestEval: Summarization Asks for Fact-based Evaluation , 2021, EMNLP.

[18]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[19]  Li Yujian,et al.  A Normalized Levenshtein Distance Metric , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Richard Socher,et al.  Neural Text Summarization: A Critical Evaluation , 2019, EMNLP.

[21]  Fei Liu,et al.  Guiding Extractive Summarization with Question-Answering Rewards , 2019, NAACL.

[22]  Yejin Choi,et al.  The Curious Case of Neural Text Degeneration , 2019, ICLR.

[23]  Alex Wang,et al.  Asking and Answering Questions to Evaluate the Factual Consistency of Summaries , 2020, ACL.

[24]  Michael Elhadad,et al.  Question Answering as an Automatic Evaluation Metric for News Article Summarization , 2019, NAACL.

[25]  Ryan McDonald,et al.  On Faithfulness and Factuality in Abstractive Summarization , 2020, ACL.

[26]  Fei Wu,et al.  A Semantic QA-Based Approach for Text Summarization Evaluation , 2017, AAAI.

[27]  Alec Radford,et al.  Proximal Policy Optimization Algorithms , 2017, ArXiv.

[28]  Bowen Zhou,et al.  Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond , 2016, CoNLL.

[29]  Peter J. Liu,et al.  PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization , 2019, ICML.

[30]  Aleksander Wawer,et al.  SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization , 2019, EMNLP.

[31]  Lingfei Wu,et al.  Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward , 2020, ACL.

[32]  Xuedong Huang,et al.  Boosting Factual Correctness of Abstractive Summarization with Knowledge Graph , 2020, ArXiv.