A framework for multi-document abstractive summarization based on semantic role labelling

We propose a framework for abstractive summarization of multi-documents, which aims to select contents of summary not from the source document sentences but from the semantic representation of the source documents. In this framework, contents of the source documents are represented by predicate argument structures by employing semantic role labeling. Content selection for summary is made by ranking the predicate argument structures based on optimized features, and using language generation for generating sentences from predicate argument structures. Our proposed framework differs from other abstractive summarization approaches in a few aspects. First, it employs semantic role labeling for semantic representation of text. Secondly, it analyzes the source text semantically by utilizing semantic similarity measure in order to cluster semantically similar predicate argument structures across the text; and finally it ranks the predicate argument structures based on features weighted by genetic algorithm (GA). Experiment of this study is carried out using DUC-2002, a standard corpus for text summarization. Results indicate that the proposed approach performs better than other summarization systems.     

融合多信息句子图模型的多文档摘要抽取

针对现有多文档抽取方法不能很好地利用句子主题信息和语义信息的问题,提出一种融合多信息句子图模型的多文档摘要抽取方法。首先,以句子为节点,构建句子图模型;然后,将基于句子的贝叶斯主题模型和词向量模型得到的句子主题概率分布和句子语义相似度相融合,得到句子最终的相关性,结合主题信息和语义信息作为句子图模型的边权重;最后,借助句子图最小支配集的摘要方法来描述多文档摘要。该方法通过融合多信息的句子图模型,将句子间的主题信息、语义信息和关系信息相结合。实验结果表明,该方法能够有效地改进抽取摘要的综合性能。     

主题信息的中文多文档自动文摘系统

多文档自动文摘能够帮助人们自动、快速地获取信息,使用主题模型构建多文档自动文摘系统是一种新的尝试,其中主题模型采用浅层狄利赫雷分配（LDA）。该模型是一个多层的产生式概率模型,能够检测文档中的主题分布。使用LDA为多文档集合建模,通过计算句子在不同主题上的概率分布之间的相似度作为句子的重要度,并根据句子重要度进行文摘句的抽取。实验结果表明,该方法所得到的文摘性能优于传统的文摘方法。     

iSpreadRank: Ranking sentences for extraction-based summarization using feature weight propagation in the sentence similarity network

Sentence extraction is a widely adopted text summarization technique where the most important sentences are extracted from document(s) and presented as a summary. The first step towards sentence extraction is to rank sentences in order of importance as in the summary. This paper proposes a novel graph-based ranking method, iSpreadRank, to perform this task. iSpreadRank models a set of topic-related documents into a sentence similarity network. Based on such a network model, iSpreadRank exploits the spreading activation theory to formulate a general concept from social network analysis: the importance of a node in a network (i.e., a sentence in this paper) is determined not only by the number of nodes to which it connects, but also by the importance of its connected nodes. The algorithm recursively re-weights the importance of sentences by spreading their sentence-specific feature scores throughout the network to adjust the importance of other sentences. Consequently, a ranking of sentences indicating the relative importance of sentences is reasoned. This paper also develops an approach to produce a generic extractive summary according to the inferred sentence ranking. The proposed summarization method is evaluated using the DUC 2004 data set, and found to perform well. Experimental results show that the proposed method obtains a ROUGE-1 score of 0.38068, which represents a slight difference of 0.00156, when compared with the best participant in the DUC 2004 evaluation.     

PSG: a two-layer graph model for document summarization

Graph model has been widely applied in document summarization by using sentence as the graph node, and the similarity between sentences as the edge. In this paper, a novel graph model for document summarization is presented, that not only sentences relevance but also phrases relevance information included in sentences are utilized. In a word, we construct a phrase-sentence two-layer graph structure model (PSG) to summarize document(s). We use this model for generic document summarization and query-focused summarization. The experimental results show that our model greatly outperforms existing work.     

案件要素句子关联图卷积的案件舆情摘要方法

案件舆情摘要是从涉及特定案件的新闻文本簇中,抽取能够概括其主题信息的几个句子作为摘要.案件舆情摘要可以看作特定领域的多文档摘要,与一般的摘要任务相比,可以通过一些贯穿于整个文本簇的案件要素来表征其主题信息.在文本簇中,由于句子与句子之间存在关联关系,案件要素与句子亦存在着不同程度的关联关系,这些关联关系对摘要句的抽取有着重要的作用.提出了基于案件要素句子关联图卷积的案件文本摘要方法,采用图的结构来对多文本簇进行建模,句子作为主节点,词和案件要素作为辅助节点来增强句子之间的关联关系,利用多种特征计算不同节点间的关联关系.然后,使用图卷积神经网络学习句子关联图,并对句子进行分类得到候选摘要句.最后,通过去重和排序得到案件舆情摘要.在收集到的案件舆情摘要数据集上进行实验,结果表明：提出的方法相比基准模型取得了更好的效果,引入要素及句子关联图对案件多文档摘要有很好的效果.     

基于词项—句子—文档三层图模型的多文档自动摘要

应用图模型来研究多文档自动摘要是当前研究的一个热点,它以句子为顶点,以句子之间相似度为边的权重构造无向图结构。由于此模型没有充分考虑句子中的词项权重信息以及句子所属的文档信息,针对这个问题,该文提出了一种基于词项—句子—文档的三层图模型,该模型可充分利用句子中的词项权重信息以及句子所属的文档信息来计算句子相似度。在DUC2003和DUC2004数据集上的实验结果表明,基于词项—句子—文档三层图模型的方法优于LexRank模型和文档敏感图模型。     

Hybrid method for text summarization based on statistical and semantic treatment

Text summarization presents several challenges such as considering semantic relationships among words, dealing with redundancy and information diversity issues. Seeking to overcome these problems, we propose in this paper a new graph-based Arabic summarization system that combines statistical and semantic analysis. The proposed approach utilizes ontology hierarchical structure and relations to provide a more accurate similarity measurement between terms in order to improve the quality of the summary. The proposed method is based on a two-dimensional graph model that makes uses statistical and semantic similarities. The statistical similarity is based on the content overlap between two sentences, while the semantic similarity is computed using the semantic information extracted from a lexical database whose use enables our system to apply reasoning by measuring semantic distance between real human concepts. The weighted ranking algorithm PageRank is performed on the graph to produce significant score for all document sentences. The score of each sentence is performed by adding other statistical features. In addition, we address redundancy and information diversity issues by using an adapted version of Maximal Marginal Relevance method. Experimental results on EASC and our own datasets showed the effectiveness of our proposed approach over existing summarization systems.

     

A document-sensitive graph model for multi-document summarization

In recent years, graph-based models and ranking algorithms have drawn considerable attention from the extractive document summarization community. Most existing approaches take into account sentence-level relations (e.g. sentence similarity) but neglect the difference among documents and the influence of documents on sentences. In this paper, we present a novel document-sensitive graph model that emphasizes the influence of global document set information on local sentence evaluation. By exploiting document–document and document–sentence relations, we distinguish intra-document sentence relations from inter-document sentence relations. In such a way, we move towards the goal of truly summarizing multiple documents rather than a single combined document. Based on this model, we develop an iterative sentence ranking algorithm, namely DsR (Document-Sensitive Ranking). Automatic ROUGE evaluations on the DUC data sets show that DsR outperforms previous graph-based models in both generic and query-oriented summarization tasks.     

Concept generalization and fusion for abstractive sentence generation

Text summarization is either extractive or abstractive. Extractive summarization is to select the most salient pieces of information (words, phrases, and/or sentences) from a source document without adding any external information. Abstractive summarization allows an internal representation of the source document so as to produce a faithful summary of the source. In this case, external text can be inserted into the generated summary. Because of the complexity of the abstractive approach, the vast majority of work in text summarization has adopted an extractive approach.In this work, we focus on concepts fusion and generalization, i.e. where different concepts appearing in a sentence can be replaced by one concept which covers the meanings of all of them. This is one operation that can be used as part of an abstractive text summarization system. The main goal of this contribution is to enrich the research efforts on abstractive text summarization with a novel approach that allows the generalization of sentences using semantic resources. This work should be useful in intelligent systems more generally since it introduces a means to shorten sentences by producing more general (hence abstractions of the) sentences. It could be used, for instance, to display shorter texts in applications for mobile devices. It should also improve the quality of the generated text summaries by mentioning key (general) concepts. One can think of using the approach in reasoning systems where different concepts appearing in the same context are related to one another with the aim of finding a more general representation of the concepts. This could be in the context of Goal Formulation, expert systems, scenario recognition, and cognitive reasoning more generally.We present our methodology for the generalization and fusion of concepts that appear in sentences. This is achieved through (1) the detection and extraction of what we define as generalizable sentences and (2) the generation and reduction of the space of generalization versions. We introduce two approaches we have designed to select the best sentences from the space of generalization versions. Using four NLTK¹ corpora, the first approach estimates the “acceptability” of a given generalization version. The second approach is Machine Learning-based and uses contextual and specific features. The recall, precision and F1-score measures resulting from the evaluation of the concept generalization and fusion approach are presented.     

多文档文摘中句子优化选择方法研究

在多文档文摘子主题划分的基础上，提出了一种在子主题之间对文摘句优化选择的方法．首先在句子相似度计算的基础上，形成多文档集合的子主题，通过对各子主题打分，确定子主题的抽取顺序．以文摘中有效词的覆盖率作为优化指标，在各个子主题中选择文摘句．从减少子主题之间及子主题内部的信息的冗余性两个角度选择文摘句，使文摘的信息覆盖率得到很大提高．实验表明，生成的文摘是令人满意的．     

融合主题特征的文本自动摘要方法研究

针对传统图模型方法进行文本摘要时只考虑统计特征或浅层次语义特征,缺乏对深层次主题语义特征的挖掘与利用,提出了融合主题特征后多维度度量的文本自动摘要方法MDSR(multi-dimension summarization rank)。首先利用LDA主题模型对文本主题语义信息进行挖掘,定义了主题重要度以衡量主题特征对句子重要程度的影响;然后结合主题特征、统计特征和句间相似度,改进了图模型节点的概率转移矩阵的构建方式;最后根据句子节点权重进行摘要的抽取与度量。实验结果显示,当主题特征、统计特征及句间相似度权重比例达到3:4:3时,MDSR方法的ROUGE评测值达到最佳,ROUGE-1、ROUGE-2、ROUGE-SU4值分别达到53.35%、35.18%和33.86%,优于对比方法,表明了融入主题特征后的文本摘要方法有效提高了摘要抽取的准确性。     

基于事件项语义图聚类的多文档摘要方法

基于事件的抽取式摘要方法一般首先抽取那些描述重要事件的句子,然后把它们重组并生成摘要。该文将事件定义为事件项以及与其关联的命名实体,并聚焦从外部语义资源获取的事件项语义关系。首先基于事件项语义关系创建事件项语义关系图并使用改进的DBSCAN算法对事件项进行聚类,接着为每类选择一个代表事件项或者选择一类事件项来表示文档集的主题,最后从文档抽取那些包含代表项并且最重要的句子生成摘要。该文的实验结果证明在多文档自动摘要中考虑事件项语义关系是必要的和可行的。     

Recent advances in document summarization

The task of automatic document summarization aims at generating short summaries for originally long documents. A good summary should cover the most important information of the original document or a cluster of documents, while being coherent, non-redundant and grammatically readable. Numerous approaches for automatic summarization have been developed to date. In this paper we give a self-contained, broad overview of recent progress made for document summarization within the last 5 years. Specifically, we emphasize on significant contributions made in recent years that represent the state-of-the-art of document summarization, including progress on modern sentence extraction approaches that improve concept coverage, information diversity and content coherence, as well as attempts from summarization frameworks that integrate sentence compression, and more abstractive systems that are able to produce completely new sentences. In addition, we review progress made for document summarization in domains, genres and applications that are different from traditional settings. We also point out some of the latest trends and highlight a few possible future directions.     

基于加权TextRank的中文自动文本摘要

现有中文自动文本摘要方法主要是利用文本自身信息,其缺陷是不能充分利用词语之间的语义相关等信息。鉴于此,提出了一种改进的中文文本摘要方法。此方法将外部语料库信息用词向量的形式融入到TextRank算法中,通过TextRank与word2vec的结合,把句子中每个词语映射到高维词库形成句向量。充分考虑了句子之间的相似度、关键词的覆盖率和句子与标题的相似度等因素,以此计算句子之间的影响权重,并选取排序最靠前的句子重新排序作为文本的摘要。实验结果表明,此方法在本文数据集中取得了较好的效果,自动提取中文摘要的效果比原方法好。     

基于深度学习的文本自动摘要方案

针对自然语言处理（NLP）生成式自动摘要领域的语义理解不充分、摘要语句不通顺和摘要准确度不够高的问题，提出了一种新的生成式自动摘要解决方案，包括一种改进的词向量生成技术和一个生成式自动摘要模型。改进的词向量生成技术以Skip-Gram方法生成的词向量为基础，结合摘要的特点，引入词性、词频和逆文本频率三个词特征，有效地提高了词语的理解；而提出的Bi-MulRnn+生成式自动摘要模型以序列映射（seq2seq）与自编码器结构为基础，引入注意力机制、门控循环单元（GRU）结构、双向循环神经网络（BiRnn）、多层循环神经网络（MultiRnn）和集束搜索，提高了生成式摘要准确性与语句流畅度。基于大规模中文短文本摘要（LCSTS）数据集的实验结果表明，该方案能够有效地解决短文本生成式摘要问题，并在Rouge标准评价体系中表现良好，提高了摘要准确性与语句流畅度。     

Intra-relation or inter-relation?: Exploiting social information for Web document summarization

Traditional summarization methods only use the internal information of a Web document while ignoring its social information such as tweets from Twitter, which can provide a perspective viewpoint for readers towards an event. This paper proposes a framework named SoRTESum to take the advantages of social information such as document content reflection to extract summary sentences and social messages. In order to do that, the summarization was formulated in two steps: scoring and ranking. In the scoring step, the score of a sentence or social message is computed by using intra-relation and inter-relation which integrate the support of local and social information in a mutual reinforcement form. To calculate these relations, 16 features are proposed. After scoring, the summarization is generated by selecting top m ranked sentences and social messages. SoRTESum was extensively evaluated on two datasets. Promising results show that: (i) SoRTESum obtains significant improvements of ROUGE-scores over state-of-the-art baselines and competitive results with the learning to rank approach trained by RankBoost and (ii) combining intra-relation and inter-relation benefits single-document summarization.     

英汉《小王子》抽象语义图结构的对比分析

AMR(抽象语义表示)是国际上一种新的句子语义表示方法,有着接近于中间语言的表示能力,其研发者已经建立了英文《小王子》等AMR语料库。AMR与以往的句法语义表示方法的最大不同在于两个方面,首先采用图结构来表示句子的语义;其次允许添加原句之外的概念节点来表示隐含的语义。该文针对汉语特点,在制定中文AMR标注规范的基础上,标注完成了中文版《小王子》的AMR语料库,标注一致性的Smatch值为0.83。统计结果显示,英汉双语含图结构句子具有很高的相关性,且含有图的句子比例高达40%左右,额外添加的概念节点则存在较大差异。最后讨论了AMR在汉语句子语义表示以及跨语言对比方面的优势。     

基于BERT-PGN模型的中文新闻文本自动摘要生成

针对文本自动摘要任务中生成式摘要模型对句子的上下文理解不够充分、生成内容重复的问题,基于BERT和指针生成网络（PGN）,提出了一种面向中文新闻文本的生成式摘要模型——BERT-指针生成网络（BERT-PGN）。首先,利用BERT预训练语言模型结合多维语义特征获取词向量,从而得到更细粒度的文本上下文表示;然后,通过PGN模型,从词表或原文中抽取单词组成摘要;最后,结合coverage机制来减少重复内容的生成并获取最终的摘要结果。在2017年CCF国际自然语言处理与中文计算会议（NLPCC2017）单文档中文新闻摘要评测数据集上的实验结果表明,与PGN、伴随注意力机制的长短时记忆神经网络（LSTM-attention）等模型相比,结合多维语义特征的BERT-PGN模型对摘要原文的理解更加充分,生成的摘要内容更加丰富,全面且有效地减少重复、冗余内容的生成,Rouge-2和Rouge-4指标分别提升了1.5%和1.2%。     

Word-sentence co-ranking for automatic extractive text summarization

Extractive summarization aims to automatically produce a short summary of a document by concatenating several sentences taken exactly from the original material. Due to its simplicity and easy-to-use, the extractive summarization methods have become the dominant paradigm in the realm of text summarization. In this paper, we address the sentence scoring technique, a key step of the extractive summarization. Specifically, we propose a novel word-sentence co-ranking model named CoRank, which combines the word-sentence relationship with the graph-based unsupervised ranking model. CoRank is quite concise in the view of matrix operations, and its convergence can be theoretically guaranteed. Moreover, a redundancy elimination technique is presented as a supplement to CoRank, so that the quality of automatic summarization can be further enhanced. As a result, CoRank can serve as an important building-block of the intelligent summarization systems. Experimental results on two real-life datasets including nearly 600 documents demonstrate the effectiveness of the proposed methods.