Using AdaBoost Meta-Learning Algorithm for Medical News Multi-Document Summarization

Automatic text summarization involves reducing a text document or a larger corpus of multiple documents to a short set of sentences or paragraphs that convey the main meaning of the text. In this paper, we discuss about multi-document summarization that differs from the single one in which the issues of compression, speed, redundancy and passage selection are critical in the formation of useful summaries. Since the number and variety of online medical news make them difficult for experts in the medical field to read all of the medical news, an automatic multi-document summarization can be useful for easy study of information on the web. Hence we propose a new approach based on machine learning meta-learner algorithm called AdaBoost that is used for summarization. We treat a document as a set of sentences, and the learning algorithm must learn to classify as positive or negative examples of sentences based on the score of the sentences. For this learning task, we apply AdaBoost meta-learning algorithm where a C4.5 decision tree has been chosen as the base learner. In our experiment, we use 450 pieces of news that are downloaded from different medical websites. Then we compare our results with some existing approaches.

Constructing a taxonomy to support multi-document summarization of dissertation abstracts

This paper reports part of a study to develop a method for automatic multi-document summarization. The current focus is on dissertations, in the field of sociology. The summarization method uses macro-level and micro-level discourse structure to identify important information that can be extracted from dissertation abstracts, and then uses a variable-based framework to integrate and organize extracted information across dissertation abstracts. This framework focuses more on research concepts and their research relationships found in sociology dissertation abstracts and has a hierarchical structure. A taxonomy is constructed to support the summarization process in two ways: (1) helping to identify important concepts and relations expressed in the text, and (2) providing a structure for linking similar concepts in different abstracts. This paper describes the variable-based framework and the summarization process, and then reports the construction of the taxonomy for supporting the summarization process. An example is provided to show how to use the constructed taxonomy to identify important concepts and integrate the concepts extracted from different abstracts.

Research on multi-document summarization based on latent semantic indexing

A multi-document summarization method based on Latent Semantic Indexing (LSI) is proposed. The method combines several reports on the same issue into a matrix of terms and sentences, and uses a Singular Value Decomposition (SVD) to reduce the dimension of the matrix and extract features, and then the sentence similarity is computed. The sentences are clustered according to similarity of sentences. The centroid sentences are selected from each class. Finally, the selected sentences are ordered to generate the summarization. The evaluation and results are presented, which prove that the proposed methods are efficient.

TWO-STAGE SENTENCE SELECTION APPROACH FOR MULTI-DOCUMENT SUMMARIZATION

Compared with the traditional method of adding sentences to get summary in multi-document summarization,a two-stage sentence selection approach based on deleting sentences in acandidate sentence set to generate summary is proposed,which has two stages,the acquisition of acandidate sentence set and the optimum selection of sentence.At the first stage,the candidate sentenceset is obtained by redundancy-based sentence selection approach.At the second stage,optimum se-lection of sentences is proposed to delete sentences in the candidate sentence set according to itscontribution to the whole set until getting the appointed summary length.With a test corpus,theROUGE value of summaries gotten by the proposed approach proves its validity,compared with thetraditional method of sentence selection.The influence of the token chosen in the two-stage sentenceselection approach on the quality of the generated summaries is analyzed.

Multi-Document Summarization Model Based on Integer Linear Programming

This paper proposes an extractive generic text summarization model that generates summaries by selecting sentences according to their scores. Sentence scores are calculated using their extensive coverage of the main content of the text, and summaries are created by extracting the highest scored sentences from the original document. The model formalized as a multiobjective integer programming problem. An advantage of this model is that it can cover the main content of source (s) and provide less redundancy in the generated sum- maries. To extract sentences which form a summary with an extensive coverage of the main content of the text and less redundancy, have been used the similarity of sentences to the original document and the similarity between sentences. Performance evaluation is conducted by comparing summarization outputs with manual summaries of DUC2004 dataset. Experiments showed that the proposed approach outperforms the related methods.

Evolutionary Algorithm for Extractive Text Summarization

Text summarization is the process of automatically creating a compressed version of a given document preserving its information content. There are two types of summarization: extractive and abstractive. Extractive summarization methods simplify the problem of summarization into the problem of selecting a representative subset of the sentences in the original documents. Abstractive summarization may compose novel sentences, unseen in the original sources. In our study we focus on sentence based extractive document summarization. The extractive summarization systems are typically based on techniques for sentence extraction and aim to cover the set of sentences that are most important for the overall understanding of a given document. In this paper, we propose unsupervised document summarization method that creates the summary by clustering and extracting sentences from the original document. For this purpose new criterion functions for sentence clustering have been proposed. Similarity measures play an increasingly important role in document clustering. Here we’ve also developed a discrete differential evolution algorithm to optimize the criterion functions. The experimental results show that our suggested approach can improve the performance compared to sate-of-the-art summarization approaches.

面向司法文书的抽取-生成式自动摘要模型

为解决抽取式摘要核心信息拼接生硬,生成式摘要源文本过长易忽略重要信息等问题,对抽取式摘要和生成式摘要的结合进行研究。通过分析抽取式摘要可提取出文本关键信息且缩短源文本长度特性;生成式摘要可降低序列间信息损失,增加文本关联的优势。提出一种面向司法文书的抽取-生成式自动摘要模型,融合模型优势,避免单一模型存在的关键文本信息重复及重组段落语法不准的问题,保障法律文书抽取的切实完整性。在大规模公开法律领域裁判文书数据集上的实验结果表明,该模型获得较高ROUGE得分,表明了该模型提升了摘要质量。

结合预训练的多文档摘要:研究

新闻文本摘要任务旨在从庞大复杂的新闻文本中快速准确地提炼出简明扼要的摘要。基于预训练语言模型对多文档摘要进行研究,重点研究结合预训练任务的具体模型训练方式对模型效果提升的作用,强化多文档之间的信息交流,以生成更全面、更简练的摘要。对于结合预训练任务,提出对基线模型、预训练任务内容、预训练任务数量、预训练任务顺序的对比实验,探索标记了行之有效的预训练任务,总结归纳了强化多文档之间的信息交流的具体方法,精炼提出了简明高效的预训练流程。在公开新闻多文档数据集上进行训练和测试,实验结果表明预训练任务的内容、数量、顺序对ROUGE值都有一定提升,并且整合三者结论提出的特定预训练组合对ROUGE值有明显提升。

基于异构图和关键词的抽取式文本摘要模型

抽取式文本摘要使用一定的策略从冗长的文本中选择一些句子组成摘要,其关键在于要尽可能多地利用文本的语义信息和结构信息。为了更好地挖掘这些信息,进而利用它们指导摘要的抽取,提出了一种基于异构图和关键词的抽取式文本摘要模型(HGKSum)。该模型首先将文本建模为由句子节点和词语节点构成的异构图,在异构图上使用图注意力网络学习节点的特征,之后将关键词抽取任务作为文本摘要任务的辅助任务,使用多任务学习的方式进行训练,得到候选摘要,最后对候选摘要进行精炼以降低冗余度,得到最终摘要。在基准数据集上的对比实验表明,该模型性能优于基准模型,此外,消融实验也证明了引入异构节点和关键词的必要性。

基于异构图分层学习的细粒度多文档摘要抽取

抽取的目标是在多个文档中提取共有关键信息,其对简洁性的要求高于单文档摘要抽取。现有的多文档摘要抽取方法通常在句子级别进行建模,容易引入较多的冗余信息。为了解决上述问题,提出一种基于异构图分层学习的多文档摘要抽取框架,通过层次化构建单词层级图和子句层级图来有效建模语义关系和结构关系。针对单词层级图和子句层级图这2个异构图的学习问题,设计具有不同层次更新机制的两层学习层来降低学习多种结构关系的难度。在单词层级图学习层,提出交替更新机制更新不同的粒度节点,以单词节点为载体通过图注意网络进行语义信息传递;在子句层级图学习层,提出两阶段分步学习更新机制聚合多种结构关系,第一阶段聚合同构关系,第二阶段基于注意力聚合异构关系。实验结果表明,与抽取式基准模型相比,该框架在Multinews数据集上取得了显著的性能提升,ROUGE-1、ROUGE-2和ROUGE-L分别提高0.88、0.23和2.27,消融实验结果也验证了两层学习层及其层次更新机制的有效性。

面向中文法律裁判文书的抽取式摘要算法

裁判文书自动摘要的目的在于让计算机能够自动选择、抽取和压缩法律文本中的重要信息,从而减轻法律从业者的工作量。目前,大多数基于预训练语言模型的摘要算法对输入文本的长度存在限制,因此无法对长文本进行有效摘要。为此,该文提出了一种新的抽取式摘要算法,利用预训练语言模型生成句子向量,并基于Transformer编码器结构融合包括句子向量、句子位置和句子长度在内的信息,完成句子摘要。实验结果显示,该算法能够有效处理长文本摘要任务。此外,在2020年中国法律智能技术评测(CAIL)摘要数据集上进行测试的结果表明,与基线模型相比,该模型在ROUGE-1、ROUGE-2和ROUGE-L指标上均有显著提升。

Document Clustering Using Graph Based Fuzzy Association Rule Generation

With the wider growth of web-based documents,the necessity of automatic document clustering and text summarization is increased.Here,document summarization that is extracting the essential task with appropriate information,removal of unnecessary data and providing the data in a cohesive and coherent manner is determined to be a most confronting task.In this research,a novel intelligent model for document clustering is designed with graph model and Fuzzy based association rule generation(gFAR).Initially,the graph model is used to map the relationship among the data(multi-source)followed by the establishment of document clustering with the generation of association rule using the fuzzy concept.This method shows benefit in redundancy elimination by mapping the relevant document using graph model and reduces the time consumption and improves the accuracy using the association rule generation with fuzzy.This framework is provided in an interpretable way for document clustering.It iteratively reduces the error rate during relationship mapping among the data(clusters)with the assistance of weighted document content.Also,this model represents the significance of data features with class discrimination.It is also helpful in measuring the significance of the features during the data clustering process.The simulation is done with MATLAB 2016b environment and evaluated with the empirical standards like Relative Risk Patterns(RRP),ROUGE score,and Discrimination Information Measure(DMI)respectively.Here,DailyMail and DUC 2004 dataset is used to extract the empirical results.The proposed gFAR model gives better trade-off while compared with various prevailing approaches.

基于层级BiGRU+Attention的面向查询的新闻多文档抽取式摘要方法

针对现有大多数面向查询的多文档抽取式摘要方法通常是将句子的内容显著性及查询相关性分开计算的,且对向量表示的建模不充分的问题,提出一种基于层级BiGRU+Attention的面向查询的新闻多文档抽取式摘要方法.首先,通过训练层级BiGRU+Attention神经网络模型,获得具有丰富上下文语义信息的句子、文档向量表示;并在此过程中通过双线性变换注意力机制,使得文档向量表示不仅具有反映文档深层主旨信息的基本特性,还融入句子与用户查询的相关性信息,然后利用句向量与其进行相似度计算获得相应的句子重要性得分;其次,由句子重要性得分、句子中包含的关键词特征、句子的长度特征以及句子的时序权重系数加权组合得到最终的句子综合特征权重得分;最后,利用MMR算法来选择摘要句.实验结果表明,与其他方法相比本文提出的方法能在一定程度上提高面向查询的多文档抽取式摘要的质量,具有一定的有效性及优越性.

融合多种语义特征的代码摘要生成方法

生成任务旨在实现全自动化地产生自然语言描述源代码的功能,使其便于软件维护和程序理解。目前,主流的基于Transformer的方法只考虑源代码的文本和结构化语义特征,忽略了与源代码密切相关的API文档等外部语义特征;其次,在使用大规模数据的情况下,由于Transformer结构的自注意力模块需要计算所有相似度分数,因此存在计算成本高和内存占用量大的问题。为解决以上问题,该文提出了一种基于改进Transformer结构的融合多种语义特征的代码摘要生成方法。该方法采用三个独立编码器充分学习源代码的多种语义特征(文本、结构和外部API文档),并使用非参数化傅里叶变换替代编码器中的自注意力层,通过线性变换降低使用Transformer结构的计算时间和内存占用量,在公开数据集上的实验结果证明了该方法的有效性。

融合法条的司法裁判文书摘要生成方法

针对司法裁判文书摘要生成过程中忽略案件审理逻辑脉络,导致许多重要信息丢失的问题,基于法官的案件审理逻辑脉络,提出融合法条的裁判文书生成方法。通过构建法条的外部知识编码器,将该编码器融合到Encoder-Decoder摘要框架中,利用知识编码表示后的法条在摘要过程中辅助保留裁判文书中的重要信息,提升司法摘要生成模型的性能。实验结果表明,该模型在F1指标上相比主流的指针生成网络摘要模型分别提升了1.37 ROUGE-1、4.91 ROUGE-02、3.91 ROUGE-L。

面向法律判决文书的长文档抽取式文摘方法——BIGDCNN

针对法律判决文书信息点较多、结构化程度较高,传统的抽取式文摘方法容易产生冗余句子且无法覆盖全部关键信息的问题,提出BIGDCNN(BERT based Improved Gate Dilated Convolutional Neural Network)模型。首先将原始数据进行语料转换获取序列标注数据,再通过预训练语言模型BERT(Bidirectional Encoder Representations from Transformers)得到从词粒度到句子粒度的长文本表示;最后使用融合了改进门机制的膨胀卷积神经网络(DCNN)以及单模型融合方法,实现低冗余度提取原文关键信息的同时增强抗干扰性,并减小了梯度消失的风险。在法律判决文书自动文摘实验中,本模型的ROUGE-1、ROUGE-2、ROUGE-L评分为62.85%、46.56%、59.25%,较主流模型BERT+Transformer分别提升了15.10、15.75、12.97个百分点。BIGDCNN模型解决了传统抽取式文摘方法的问题,可以高效地运用在法律判决文书的自动文摘场景中。

中文新闻文本多文档摘要生成

针对自动文本摘要任务中多文档生成式摘要模型抽取文本特征不充分、无法捕获跨文档关系和生成内容重复的问题,提出一种多文档生成式摘要模型Transformer-PGN。利用融合段落注意力机制的Transformer结构对文本进行特征抽取,同时捕获跨文档关系;通过指针生成网络逐词生成摘要;结合覆盖率机制避免生成重复单词,形成最终的摘要。实验结果表明,与指针生成网络等模型相比,该模型生成的摘要信息更丰富、冗余度更低,Rouge-1、Rouge-2和Rouge-L分别提升了2.1%、2.4%和2.3%。

一种改进的TextRank多文档文摘自动抽取模型

多文档自动文摘通过自然语言处理技术从多篇同主题的文档中提取概述性信息,可有效缓解信息负载问题,有助于用户迅速准确获取原文核心内容。针对中文文本特点,构建一种基于TextRank算法改进的多文档文摘自动抽取模型。首先通过预训练Word2Vec词向量模型与SIF方法融合,在中文维基百科语料库上进行预训练,获取文档中所有句子的句向量;然后借助余弦相似度构造TextRank句子间的边关系;最后使用MMR算法对文摘句进行冗余处理,得到全面又多样的文摘。通过ROUGE-N评价指标对模型进行性能评价,实验结果表明,所提模型的ROUGE-1、ROUGE-2、ROUGE-L指标值分别为0.549、0.322、0.357,均优于传统TextRank方法和Word2vec(实验样本语料)+TextRank+MMR模型,文摘质量更高。

基于PageRank的中文多文档文本情感摘要

文本情感摘要任务旨在对带有情感的文本数据进行浓缩、提炼进而产生文本所表达的关于情感意见的摘要。该文主要研究基于多文档的文本情感摘要问题,重点针对网络上存在同一个产品的多个评论产生相应的摘要。首先,为了进行关于文本情感摘要的研究,该文收集并标注了一个基于产品评论的中文多文档文本情感摘要语料库。其次,该文提出了一种基于情感信息的PageRank算法框架用于实现多文档文本情感摘要,该算法同时考虑了情感和主题相关两方面的信息。实验结果表明,该文采用的方法和已有的方法相比在ROUGE值上有显著提高。