Imitating Human Literature Review Writing: An Approach to Multi-document Summarization

Jaidka, Kokil; Khoo, Christopher S. G.; Na, Jin‐Cheon

doi:10.1007/978-3-642-13654-2_14

Cited by 12 publications

(24 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scientific document summarization is a challenging task. Multiple models trained on small datasets exist for this task (Hu and Wan, 2014;Jaidka et al, 2013;Hoang and Kan, 2010), as there are no available large-scale datasets (before this paper). Attempts at creating scientific summarization datasets have been emerging, but not to the scale required for training neural-based models.…”

Section: Related Workmentioning

confidence: 99%

Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles

Lu¹,

Dong²,

Charlin³

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Multi-document summarization is a challenging task for which there exists little largescale datasets. We propose Multi-XScience, a large-scale multi-document summarization dataset created from scientific articles. Multi-XScience introduces a challenging multidocument summarization task: writing the related-work section of a paper based on its abstract and the articles it references. Our work is inspired by extreme summarization, a dataset construction protocol that favours abstractive modeling approaches. Descriptive statistics and empirical results-using several state-of-the-art models trained on the Multi-XScience dataset-reveal that Multi-XScience is well suited for abstractive models. 1

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles

Lu¹,

Dong²,

Charlin³

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…In our earlier study (Khoo et al, 2011), we had conducted a linguistic analysis of the literature review sections of information science journal articles. We analyzed the texts at two levels of detail (Jaidka et al, 2010):…”

Section: /19mentioning

confidence: 99%

Literature review writing: how information is selected and transformed

Jaidka

Khoo

2013

Aslib Proceedings

Self Cite

View full text Add to dashboard Cite

Aim of The Study-This paper reports a study of researchers' preferences in selecting information from cited papers to include in a literature review, and the kinds of transformations and editing applied to the selected information. This is a part of a larger project to develop an automatic summarization method that emulates human literature review writing behaviour. Research Questions-How are literature reviews written-where do authors select information from, what types of information do they select and how do they transform it? What is the relationship between styles of literature review (integrative and descriptive) and each of these variables (source sections, types of information and types of transformation)? Method-We analyzed the literature review sections of 20 articles from the Journal of the American Society for Information Science & Technology, 2001-2008, to answer these questions. Referencing sentences were mapped to 279 source papers to determine the source sentences. The type of information selected, the sections of source papers where the information was taken from, and the types of editing changes made to include in the literature review were analyzed. Findings-Integrative literature reviews contain more research result information and critique, and reference more information from the Results and Conclusion sections of the source papers. Descriptive literature reviews contain more research method information, and reference more information from the Abstract and Introduction sections. The most common kind of transformation is the high-level summary, though descriptive literature reviews have more cut-pasting, especially for information taken from the Abstract. The types of editing-substitutions, insertions and deletions-applied to the source sentences are identified. Practical Implications-The results are useful in the teaching of literature review writing, and indicate ways for automatic summarization systems to emulate human literature review writing. Originality/Value-Though there have been several studies of abstracts and abstracting, there are few studies of literature reviews and literature review writing.

show abstract

“…Some schema and template based approaches have been used successfully in achieving coherence (e.g. (Sauper, Barzilay, 2009;Jaidka et al, 2010)); however, they are either domain dependent or applied to a very structured domain (e.g. Wikipedia pages).…”

Section: Figure 1 Sample Summariesmentioning

confidence: 99%

“…(Cline, Nutter, 1994)) where specific schemata were designed according to the specific applications. In more recent work, (Jaidka et al, 2010;Sauper, Barzilay, 2009) also tried to utilize discourse structures learned from domain relevant articles (e.g. scientific research paper) to design schemata (or templates) for summarization.…”

Section: Related Workmentioning

confidence: 99%

L'utilisation de schémas de discours pour améliorer la pertinence et la cohérence discursive dans le cadre du résumé automatique de blogs

Mithun¹,

Kosseim²

2012

Document numérique

View full text Add to dashboard Cite

Question irrelevance and discourse incoherence are important and typical problems in multi-document summarization especially when dealing with informal and opinionated texts. To address these two issues, we propose a domain-independent query-based summarization approach for opinionated documents that uses intra-sentential discourse structures in the framework of schemata. We have developed a generic domain-independent schema-based approach that selects the most appropriate text schema to answer specific types of questions. The schemata define the content and the organization of summaries based on the discourse relations present in candidate sentences. To decide which candidate sentences should be included in the final summary and where, each sentence is automatically tagged with the rhetorical predicates it conveys and allowed to fill a slot of the schema. Finally post-schema heuristics that work at the inter-sentence level are used to improve coherence further. To validate our approach, we have built a system named BlogSum and have evaluated its performance for question relevance and coherence using two datasets: blogs and reviews. ROUGE scores show that our approach is effective at reducing question irrelevant sentences and a manual evaluation shows a significant improvement in question relevance and coherence compared to the original candidate list. These results indicate that the use of discourse relations combined with text schemas can effectively reduce question irrelevance and discourse incoherence even with informal and opinionated documents. RÉSUMÉ. Les problèmes de pertinence et de cohérence discursive sont des enjeux importants et usuels dans le cadre du résumé automatique à partir de documents multiples, en particulier, lorsque les documents sources sont informels et sont fondés sur des opinions plutôt que des faits. Pour faire face à ces problèmes, nous proposons une approche pour le résumé automatique à partir de requêtes (query-based summarisation) qui utilise les relations de discours intra-phrastiques jumelées à des schémas textuels. Nous avons développé une approche Document numérique-n o 2/2012, 91-120 Cet article des Editions Lavoisier est disponible en acces libre et gratuit sur dn.revuesonline.com 92 DN. Volume 15-n o 2/2012 générique et indépendante du domaine qui sélectionne le schéma textuel le plus approprié pour répondre à certains types de questions. Les schémas définissent le contenu et l'organisation des résumés en se basant sur les relations de discours présentes dans les phrases candidates. Pour sélectionner quelles phrases devraient être incluses dans le résumé et où, chaque phrase est automatiquement étiquetée par les relations rhétoriques qu'elle contient permettant ainsi de remplir des positions spécifiques dans le schéma textuel. Finalement, des heuristiques postschéma oeuvrant au niveau inter-phrastique sont utilisées pour améliorer la cohérence. Pour valider notre approche, nous avons développé un système nommé BlogSum et avons évalué ses performances vis-à-vis de la pertine...

show abstract

Imitating Human Literature Review Writing: An Approach to Multi-document Summarization

Cited by 12 publications

References 5 publications

Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles

Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles

Literature review writing: how information is selected and transformed

L'utilisation de schémas de discours pour améliorer la pertinence et la cohérence discursive dans le cadre du résumé automatique de blogs

Contact Info

Product

Resources

About