首页/论文/2004.05755

arXiv 2004.057552020-04-13cs.CLcs.IRcs.LG

Aspect and Opinion Aware Abstractive Review Summarization with Reinforced Hard Typed Decoder

Tsinghua University（清华大学）；Singapore Management University（新加坡管理大学）

Yufei Tian, Jianfei Yu, Jing Jiang

DOI：: 10.1145/3357384.3358142

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

In this paper, we study abstractive review summarization.Observing that review summaries often consist of aspect words, opinion words and context words, we propose a two-stage reinforcement learning approach, which first predicts the output word type from the three types, and then leverages the predicted word type to generate the final word distribution.Experimental results on two Amazon product review datasets demonstrate that our method can consistently outperform several strong baseline approaches based on ROUGE scores.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Multi-Reward Reinforced Summarization with Saliency and Entailment

UNC Chapel Hill（北卡罗来纳大学教堂山分校(UNC Chapel Hill)）

Abstractive text summarization is the task of compressing and rewriting a long document into a short summary while maintaining saliency, directed logical entailment, and non-redundancy. In this work, we address these three important aspects of a good summary via a reinforcement learning approach with two novel reward functions: ROUGESal and Entail, on top of a coverage-based baseline. The ROUGESal reward modifies the ROUGE metric by up-weighting the salient phrases/words detected via a keyphrase classifier. The Entail reward gives high (length-normalized) scores to logically-entailed summaries…

2018-05-29cs.AIcs.CLcs.LG

Attractive or Faithful? Popularity-Reinforced Learning for Inspired Headline Generation

National Chiao Tung University（国立交通大学）；National Tsing Hua University（国立清华大学）；Academia Sinica（中央研究院）

With the rapid proliferation of online media sources and published news, headlines have become increasingly important for attracting readers to news articles, since users may be overwhelmed with the massive information. In this paper, we generate inspired headlines that preserve the nature of news articles and catch the eye of the reader simultaneously. The task of inspired headline generation can be viewed as a specific form of Headline Generation (HG) task, with the emphasis on creating an attractive headline from a given news article. To generate inspired headlines, we propose a novel frame…

2020-02-06cs.CLcs.LG

A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization

Tencent Data Center of SNG（腾讯社交网络事业群数据中心）；Columbia University（哥伦比亚大学）；Tencent AI Lab（腾讯AI实验室）

In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST) for optimization. Through jointly attending to topics and word-level alignment, our approach can improve coherence, diversity, and informativeness of generated summaries via a biased probability generation mechanism. On the other hand, reinforcement training, like SCST, directly optimizes the proposed model with respect to the non-differentiable metric ROUGE,…

2020-07-27cs.CLcs.LGstat.ML

Reinforced Generative Adversarial Network for Abstractive Text Summarization

Sequence-to-sequence models provide a viable new approach to generative summarization, allowing models that are no longer limited to simply selecting and recombining sentences from the original text. However, these models have three drawbacks: their grasp of the details of the original text is often inaccurate, and the text generated by such models often has repetitions, while it is difficult to handle words that are beyond the word list. In this paper, we propose a new architecture that combines reinforcement learning and adversarial generative networks to enhance the sequence-to-sequence att…

2021-08-18cs.CLcs.LG

Deep Reinforced Self-Attention Masks for Abstractive Summarization (DR.SAS)

Stanford（斯坦福大学）

We present a novel architectural scheme to tackle the abstractive summarization problem based on the CNN/DMdataset which fuses Reinforcement Learning (RL) withUniLM, which is a pre-trained Deep Learning Model, to solve various natural language tasks. We have tested the limits of learning fine-grained attention in Transformers to improve the summarization quality. UniLM applies attention to the entire token space in a global fashion. We propose DR.SAS which applies the Actor-Critic (AC) algorithm to learn a dynamic self-attention distribution over the tokens to reduce redundancy and generate fa…

2019-12-30cs.CL

Reinforced Abstractive Summarization with Adaptive Length Controlling

Document summarization, as a fundamental task in natural language generation, aims to generate a short and coherent summary for a given document. Controllable summarization, especially of the length, is an important issue for some practical applications, especially how to trade-off the length constraint and information integrity. In this paper, we propose an \textbf{A}daptive \textbf{L}ength \textbf{C}ontrolling \textbf{O}ptimization (\textbf{ALCO}) method to leverage two-stage abstractive summarization model via reinforcement learning. ALCO incorporates length constraint into the stage of sen…

2022-05-13cs.CL

更多相关论文收起更多论文

A Deep Reinforced Model for Abstractive Summarization

Salesforce Research（Salesforce 研究院）

Attentional, RNN-based encoder-decoder models for abstractive summarization have achieved good performance on short input and output sequences. For longer documents and summaries however these models often include repetitive and incoherent phrases. We introduce a neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and reinforcement learning (RL). Models trained only with supervised learning often exhibit "exposure bias" - they assume ground truth i…

2017-11-13cs.CL

Answers Unite! Unsupervised Metrics for Reinforced Summarization Models

CNRS（法国国家科学研究中心）；Sorbonne Université（索邦大学）；reciTAL

Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization. RL enables to consider complex, possibly non-differentiable, metrics that globally assess the quality and relevance of the generated outputs. ROUGE, the most used summarization metric, is known to suffer from bias towards lexical similarity as well as from suboptimal accounting for fluency and readability of the generated abstracts. We thus explore and propose alternative evaluation measures: the reported human-evaluation analysis shows that the p…

2019-09-04cs.AIcs.CLcs.IR