计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (10): 344-350.doi: 10.11896/jsjkx.230800080

• 人工智能 • 上一篇    下一篇

基于多步句子选择-重写模型生成科技文献创新点

许贤哲1, 陈景强1,2   

  1. 1 南京邮电大学计算机学院 南京 210023
    2 江苏省大数据安全与智能处理重点实验室(南京邮电大学) 南京 210023
  • 收稿日期:2023-08-14 修回日期:2024-01-10 出版日期:2024-10-15 发布日期:2024-10-11
  • 通讯作者: 陈景强(cjq@njupt.edu.cn)
  • 作者简介:(cjq@njupt.edu.cn)
  • 基金资助:
    国家自然科学基金(61806101);江苏省高校自然科学研究项目(21KIB520017)

Generation of Contributions of Scientific Paper Based on Multi-step Sentence Selecting-and-Rewriting Model

XU Xianzhe1, CHEN Jingqiang1,2   

  1. 1 School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China
    2 Jiangsu Key Laboratory of Big Data Security & Intelligent Processing(Nanjing University of Posts and Telecommunications),Nanjing 210023,China
  • Received:2023-08-14 Revised:2024-01-10 Online:2024-10-15 Published:2024-10-11
  • About author:XU Xianzhe,born in 1999,postgra-duate.His main research interests include text summarization and natural language processing.
    CHEN Jingqiang,born in 1983,Ph.D,associate professor.His main research interests include text summarization and natural language processing.
  • Supported by:
    National Natural Science Foundation of China(61806101) and Natural Science Foundation of the Jiangsu Higher Education Institutions of China(21KIB520017).

PDF (PC)

220

摘要： 近年来科技文献数量的显著增加,使得研究人员难以跟上自己所在领域的最新进展。为了保持对前沿研究的追踪,研究者通常依赖于阅读文献中的创新点,该部分简明扼要地概括了关键研究成果。然而,许多作者在文中并未充分地呈现文章的创新内容,这导致读者难以快速掌握研究的核心内容。为了解决这一问题,提出了一个全新的任务,即自动生成科技文献的创新点摘要。该任务的难点之一在于目前缺少相关数据集,于是构建了科技创新点摘要语料库(SCSC)。另一个难点在于目前现有的生成式或抽取式模型在生成创新点方面分别存在冗余度过高和句与句之前缺乏关联性的问题。为了满足生成简洁、高质量创新点的需求,提出了MSSRsum模型(一个多步句子选择-重写模型)。最终实验表明,所提模型在SCSC和arXiv数据集上优于基线模型。

关键词: 摘要, 科技文献, 多步句子选择-重写, 生成创新点

Abstract: There has been a significant surge in the number of scientific papers published in recent years,which makes it challen-ging for researchers to keep up with the latest advancements in their fields.To stay updated,researchers often rely on reading the contributions section of papers,which serves as a concise summary of the key research findings.However,it is not uncommon for authors to inadequately present the innovative content of their articles,making it difficult for readers to quickly grasp the essence of the research.To address this issue,we propose a novel task of contribution summarization to automatically generate contribution summaries of scientific papers.One of the challenges of this task is the lack of relevant datasets.Therefore,we construct a scientific contribution summarization corpus(SCSC).Another issue lies in the fact that currently available abstractive or extractive models tend to suffer from either excessive redundancy or a lack of coherence between sentences.To meet the demand of ge-nerating concise and high-quality contribution sentences,we present MSSRsum,a multi-step sentence selecting-and-rewriting model.Experiments show that the proposed model outperforms baselines on SCSC and arXiv datasets.

Key words: Summarization, Scientific papers, Multi-step sentence selecting-and-rewriting, Generation of contributions

中图分类号: 

  • TP391
[1]YU T Z,SU D,DAI W L,et al.Dimsum @LaySumm 20[C]//Proceedings of the First Workshop on Scholarly Document Processing,Online:Association for Computational Linguistics.2020:303-309.
[2]CAGLIERO L,LA QUATRA M.Extracting highlights of scientific articles:A supervised summarization approach [J].Expert Systems with Applications,2020,160:113659.
[3]NARAYAN S,COHEN S B,LAPATA M.Ranking sentencesfor extractive summarization with reinforcement learning[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.New Orleans:Association for Computational Linguistics,2018:1747-1759.
[4]ZHANG S Y,DAVID W,MOHIT B.Extractive is not Faithful:An Investigation of Broad Unfaithfulness Problems in Extractive Summarization[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.Toronto,Canada:Association for Computational Linguistics,2023:2153-2174.
[5]AKANKSHA J,EDUARDO F,ENRIQUE A,et al.Deep-Summ:Exploiting topic models and sequence to sequence networks for extractive text summarization[J].Expert Systems with Applications,2023,211:118442
[6]XIAO L,WANG L,HE H,et al.Copy or rewrite:Hybrid summarization with hierarchical reinforcement learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.New York:AAAI,2020:9306-9313.
[7]SANGHWAN B,TAEUK K,JIHOON K,et al.Summary Level Training of Sentence Rewriting for Abstractive Summarization[C]//Proceedings of the 2nd Workshop on New Frontiers in Summarization.Hong Kong,China:Association for Computational Linguistics,2019:10-20.
[8]CHEN Y C,BANSAL M.Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.Melbourne,Australia:Association for Computational Linguistics,2018:675-686.
[9]CHEN J,ZHUGE H.Summarization of scientific documents bydetecting common facts in citations[J].Future Generation Computer Systems,2014,32:246-252.
[10]LI P,LU W,CHENG Q.Generating a related work section for scientific papers:an optimized approach with adopting problem and method information [J].Scientometrics,2022,127(8):4397-4417.
[11]CHEN J Q,CAI C X,JIANG X R,et al.Comparative graph-based summarization of scientific papers guided by comparative citations[C]//Proceedings of the 29th International Conference on Computational Linguistics.Gyeongju,Republic of Korea:International Committee on Computational Linguistics,2022;5978-5988.
[12]MISHRA S K,SAINI N,SAHA S,et al.Scientific document summarization in multi-objective clustering framework [J].Applied Intelligence,2022,52(2):1520-1543.
[13]HE J X,KRYSCINSKI W,MCCANN B,et al.CTRLsum:Towards Generic Controllable Text Summarization[C]//Procee-dings of the 2022 Conference on Empirical Methods in Natural Language Processing.Abu Dhabi,United Arab Emirates:Association for Computational Linguistics,2022:5879-5915.
[14]ED C,ISABELLE A,SEBASTIAN R.A Supervised Approach to Extractive Summarisation of Scientific Papers[C]//Procee-dings of the 21st Conference on Computational Natural Language Learning.Vancouver,Canada:Association for Computational Linguistics,2017:195-205.
[15]BAO G,ZHANG Y.Contextualized rewriting for text summarization [J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2023,31:1624-1635.
[16]ARMAN C,FRANCK D,DOO S K,et al. A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics.New Orleans,Louisiana:Association for Computational Linguistics,2018:615-621.
[17]NALLAPATI R,ZHOU B W,DOS SANTOS C,et al.Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond [C]//Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning.Berlin,Germany:Association for Computational Linguistics,2016:280-290.
[18]IZ B,KYLE L,ARMAN C.SciBERT:A Pretrained Language Model for Scientific Text[C]//Proceedings of the 2019 Confe-rence on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.Hong Kong,China:Association for Computational Linguistics,2019:3615-3620.
[19]NILS R,IRYNA G.Sentence-BERT:Sentence Embeddingsusing Siamese BERT-Networks[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Proces-sing and the 9th International Joint Conference on Natural Language Processing.Hong Kong,China:Association for Computational Linguistics,2019:3982-3992.
[20]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.California:Neural Information Processing Systems,2017:6000-6010.
[21]WALEED A,DIRK G,CHANDRA B,et al.Construction of the Literature Graph in Semantic Scholar[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.New Orleans-Louisiana:Association for Computational Linguistics,2018:84-91.
[22]LIN C Y.ROUGE:A package for automatic evaluation of summaries[C]//Text Summarization Branches Out.Barcelona,Spain:Association for Computational Linguistics,2004:74-81.
[23]KINGMA D P,BA J.Adam:A method for stochastic optimization[J].CoRR,2014,1412:6980.
[24]ERKAN G,RADEV D R.Lexrank:Graph-based lexical centrality as salience in text summarization [J].Journal of Artificial Intelligence Research,2004,22:57-479.
[25]VINYALS O,FORTUNATO M,JAITLY N.Pointer networks [C]//Proceedings of the 28th International Conference on Neural Information Processing Systems.Montreal:Neural Information Processing Systems,2015:2692-2700.
[26]GU N,ASH E,HAHNLOSER R H.MemSum:Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.Dublin,Ireland:Association for Computational Linguistics,2022:6507-6522.
[27]SEE A,LIU P J,MANNING C D.Get to the point:Summarization with pointer-generator networks[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.Vancouver,Canada:Association for Computational Linguistics.2017:1073-1083.
[28]ZHANG H,CAI J,XU J,et al.Pretraining-based natural lan-guage generation for text summarization[C]//Proceedings of the 23rd Conference on Computational Natural Language Lear-ning(CoNLL).Hong Kong:Association for Computational Linguistics,2019:789-797.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发