检索结果-南通市图书馆

Weakly Supervised abstractive summarization with Enhancing Factual Consistency for Chinese Complaint Reports

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第6期75卷 6201-6217页

作者： Ren Tao Chen Shuang Software College Northeastern UniversityShenyang110000China

A large variety of complaint reports reflect subjective information expressed by citizens.A key challenge of text summarization for complaint reports is to ensure the factual consistency of generated ***,in this paper,a simple and weakly supervised framework considering factual consistency is proposed to generate a summary of city-based complaint reports without pre-labeled sentences/***,it considers the importance of entity in complaint reports to ensure factual consistency of *** results on the customer review datasets(Yelp and Amazon)and complaint report dataset(complaint reports of Shenyang in China)show that the proposed framework outperforms state-of-the-art approaches in ROUGE scores and human *** unveils the effectiveness of our approach to helping in dealing with complaint reports.

关键词： Automatic summarization abstractive summarization weakly supervised training entity recognition

Enhancing N-Gram Based Metrics with Semantics for Better Evaluation of abstractive Text summarization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2022年第5期37卷 1118-1133页

作者： Jia-Wei He Wen-Jun Jiang Guo-Bang Chen Yu-Quan Le Xiao-Fei Ding College of Information Science and Electronic Engineering Hunan UniversityChangsha 410082China

Text summarization is an important task in natural language processing and it has been applied in many ***,abstractive summarization has attracted many ***,the traditional evaluation metrics that consider little semantic information,are unsuitable for evaluating the quality of deep learning based abstractive summarization models,since these models may generate new words that do not exist in the original ***,the out-of-vocabulary(OOV)problem that affects the evaluation results,has not been well solved *** address these issues,we propose a novel model called ENMS,to enhance existing N-gram based evaluation metrics with *** be specific,we present two types of methods:N-gram based Semantic Matching(NSM for short),and N-gram based Semantic Similarity(NSS for short),to improve several widely-used evaluation metrics including ROUGE(Recall-Oriented Understudy for Gisting Evaluation),BLEU(Bilingual Evaluation Understudy),*** and NSS work in different *** former calculates the matching degree directly,while the latter mainly improves the similarity *** we propose an N-gram representation mechanism to explore the vector representation of N-grams(including skip-grams).It serves as the basis of our ENMS model,in which we exploit some simple but effective integration methods to solve the OOV problem *** results over the TAC AESOP dataset show that the metrics improved by our methods are well correlated with human judgements and can be used to better evaluate abstractive summarization methods.

关键词： summarization evaluation abstractive summarization hard matching semantic information

Segmented summarization and Refinement:A Pipeline for Long-Document Analysis on Social Media

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Social Computing 2024年第2期5卷 132-144页

作者： Guanghua Wang Priyanshi Garg Weili Wu the Department of Computer Science The University of Texas at DallasRichardsonTX 75080USA

Social media’s explosive growth has resulted in a massive influx of electronic documents influencing various facets of daily ***,the enormous and complex nature of this content makes extracting valuable insights *** document summarization emerges as a pivotal technique in this context,serving to distill extensive texts into concise and comprehensible *** paper presents a novel three-stage pipeline for effective long document *** proposed approach combines unsupervised and supervised learning techniques,efficiently handling large document sets while requiring minimal computational *** methodology introduces a unique process for forming semantic chunks through spectral dynamic segmentation,effectively reducing redundancy and repetitiveness in the summarization *** to previous methods,our approach aligns each semantic chunk with the entire summary paragraph,allowing the abstractive summarization model to process documents without truncation and enabling the summarization model to deduce missing information from other *** enhance the summary generation,we utilize a sophisticated rewrite model based on Bidirectional and Auto-Regressive Transformers(BART),rearranging and reformulating summary constructs to improve their fluidity and *** studies conducted on the long documents from the Webis-TLDR-17 dataset demonstrate that our approach significantly enhances the efficiency of abstractive summarization *** contributions of this paper thus offer significant advancements in the field of long document summarization,providing a novel and effective methodology for summarizing extensive texts in the context of social media.

关键词： long document summarization abstractive summarization text segmentation text alignment rewrite model spectral embedding

An Intelligent Tree Extractive Text summarization Deep Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第11期73卷 4231-4244页

作者： Abeer Abdulaziz AlArfaj Hanan Ahmed Hosni Mahmoud Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

In recent research,deep learning algorithms have presented effective representation learning models for natural *** deep learningbased models create better data representation than classical *** are capable of automated extraction of distributed representation of *** this research,we introduce a new tree Extractive text summarization that is characterized by fitting the text structure representation in knowledge base training module,and also addresses memory issues that were not addresses *** proposed model employs a tree structured mechanism to generate the phrase and text *** proposed architecture mimics the tree configuration of the text-texts and provide better feature *** also incorporates an attention mechanism that offers an additional information source to conduct better summary *** novel model addresses text summarization as a classification process,where the model calculates the probabilities of phrase and text-summary *** model classification is divided into multiple features recognition such as information entropy,significance,redundancy and *** model was assessed on two datasets,on the Multi-Doc Composition Query(MCQ)and Dual Attention Composition dataset(DAC)*** experimental results prove that our proposed model has better summarization precision *** models by a considerable margin.

关键词： Neural network architecture text structure abstractive summarization

Ext-ICAS:A Novel Self-Normalized Extractive Intra Cosine Attention Similarity summarization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第4期45卷 377-393页

作者： P.Sharmila C.Deisy S.Parthasarathy Deparment of Information Technology Thiagarajar College of EngineeringMaduraiIndia Deparment of Data Science Thiagarajar College of EngineeringMaduraiIndia

With the continuous growth of online news articles,there arises the necessity for an efficient abstractive summarization technique for the problem of information *** summarization is highly complex and requires a deeper understanding and proper reasoning to come up with its own summary *** summarization task is framed as seq2seq *** seq2seq methods perform better on short sequences;however,for long sequences,the performance degrades due to high computation and hence a two-phase self-normalized deep neural document summarization model consisting of improvised extractive cosine normalization and seq2seq abstractive phases has been proposed in this *** novelty is to parallelize the sequence computation training by incorporating feed-forward,the self-normalized neural network in the Extractive phase using Intra Cosine Attention Similarity(Ext-ICAS)with sentence dependency ***,it does not require any normalization technique *** proposed abstractive Bidirectional Long Short Term Memory(Bi-LSTM)encoder sequence model performs better than the Bidirectional Gated Recurrent Unit(Bi-GRU)encoder with minimum training loss and with fast *** proposed model was evaluated on the Cable News Network(CNN)/Daily Mail dataset and an average rouge score of 0.435 was achieved also computational training in the extractive phase was reduced by 59%with an average number of similarity computations.

关键词： abstractive summarization natural language processing sequence-tosequence learning(seq2seq) self-normalization intra(self)attention