I N T Interactive Query-Assisted Summarization via Deep Reinforcement Learning

Interactive summarization is a task that facilitates user-guided exploration of information within a document set. While one would like to employ state of the art neural models to improve the quality of interactive summarization, many such technologies cannot ingest the full document set or cannot operate at sufficient speed for interactivity. To that end, we propose two novel deep reinforcement learning models for the task that address, respectively, the subtask of summarizing salient information that adheres to user queries, and the subtask of listing suggested queries to assist users throughout their exploration. 1 In particular, our models allow encoding the interactive session state and history to refrain from redundancy. Together, these models compose a state of the art solution that addresses all of the task requirements. We compare our solution to a recent interactive summarization system, and show through an experimental study involving real users that our models are able to improve informativeness while preserving positive user experience.

[1]  Ido Dagan,et al.  iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document Exploration , 2021, EMNLP.

[2]  Ido Dagan,et al.  Extending Multi-Document Summarization Evaluation to the Interactive Setting , 2021, NAACL.

[3]  Markus Dreyer,et al.  Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters , 2021, NAACL.

[4]  Jianfeng Gao,et al.  Data Augmentation for Abstractive Query-Focused Multi-Document Summarization , 2021, AAAI.

[5]  Xiang Ren,et al.  Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning , 2020, EMNLP.

[6]  Pengfei Liu,et al.  Heterogeneous Graph Neural Networks for Extractive Document Summarization , 2020, ACL.

[7]  Tianyi Zhou,et al.  Conditional Self-Attention for Query-based Summarization , 2020, ArXiv.

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

[9]  Iryna Gurevych,et al.  Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks , 2019, EMNLP.

[10]  Yen-Chun Chen,et al.  Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting , 2018, ACL.

[11]  Ramakanth Pasunuru,et al.  Multi-Reward Reinforced Summarization with Saliency and Entailment , 2018, NAACL.

[12]  Michael Elhadad,et al.  Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models , 2018, ArXiv.

[13]  Ido Dagan,et al.  Interactive Abstractive Summarization for Event News Tweets , 2017, EMNLP.

[14]  Cornelia Caragea,et al.  PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents , 2017, ACL.

[15]  Nadine Rauh,et al.  System Latency Guidelines Then and Now - Is Zero Latency Really Considered Necessary? , 2017, HCI.

[16]  Michael Elhadad,et al.  Topic Concentration in Query Focused Summarization Datasets , 2016, AAAI.

[17]  Alex Graves,et al.  Asynchronous Methods for Deep Reinforcement Learning , 2016, ICML.

[18]  Marc'Aurelio Ranzato,et al.  Sequence Level Training with Recurrent Neural Networks , 2015, ICLR.

[19]  Samy Bengio,et al.  Order Matters: Sequence to sequence for sets , 2015, ICLR.

[20]  Wei Xu,et al.  Bidirectional LSTM-CRF Models for Sequence Tagging , 2015, ArXiv.

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

[22]  Craig MacDonald,et al.  Incremental Update Summarization: Adaptive Sentence Selection based on Prevalence and Novelty , 2014, CIKM.

[23]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[24]  Michael Elhadad,et al.  Query-Chain Focused Summarization , 2014, ACL.

[25]  Mausam,et al.  Hierarchical Summarization: Scaling Up Multi-Document Summarization , 2014, ACL.

[26]  James R. Lewis,et al.  UMUX-LITE: when there's no time for the SUS , 2013, CHI.

[27]  Yang Liu,et al.  Non-Expert Evaluation of Summarization Systems is Risky , 2010, Mturk@HLT-NAACL.

[28]  Lucy Vanderwende,et al.  Exploring Content Models for Multi-Document Summarization , 2009, NAACL.

[29]  Xiaojun Wan,et al.  Single Document Keyphrase Extraction Using Neighborhood Knowledge , 2008, AAAI.

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

[31]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[32]  Dragomir R. Radev,et al.  LexRank: Graph-based Lexical Centrality as Salience in Text Summarization , 2004, J. Artif. Intell. Res..

[33]  J. B. Brooke,et al.  SUS: A 'Quick and Dirty' Usability Scale , 1996 .

[34]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[35]  Ido Dagan,et al.  Multi-Document Keyphrase Extraction: A Literature Review and the First Dataset , 2021, ArXiv.

[36]  Fei Sha,et al.  CoMSum and SIBERT: A Dataset and Neural Model for Query-Based Multi-document Summarization , 2021, ICDAR.

[37]  Jade Goldstein-Stewart,et al.  The use of MMR, diversity-based reranking for reordering documents and producing summaries , 1998, SIGIR '98.