30,170 Hits in 8.2 sec

Towards automatic extraction of epistemic items from scientific publications

Tudor Groza, Siegfried Handschuh, Georgeta Bordea
2010 Proceedings of the 2010 ACM Symposium on Applied Computing - SAC '10  
In this paper we make the initial steps in the direction of automatic extraction of epistemic items (i.e. claims, positions, arguments) from scientific publications.  ...  The exponential growth of the World Wide Web in the last decade, brought with it an explosion in the information space.  ...  Empirical Analysis To automate the process of identifying the elementary text spans and the rhetorical relations that hold among them, we rely mostly on the discourse function of cue phrases, i.e. words  ... 
doi:10.1145/1774088.1774377 dblp:conf/sac/GrozaHB10 fatcat:5bjbxav2bjbmblxfw5apcmhnnu

Rhetorical relations for information retrieval

Christina Lioma, Birger Larsen, Wei Lu
2012 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '12  
We present a language model modification that considers rhetorical relations when estimating the relevance of a document to a query.  ...  Rhetorical relations, e.g. contrast, cause, explanation, describe how the parts of a text are linked to each other.  ...  [16] perform document sentiment analysis (partly) based on a document's discourse structure.  ... 
doi:10.1145/2348283.2348407 dblp:conf/sigir/LiomaLL12 fatcat:22s2jf26azfw7ljp73xhn7ivgq

Rhetorical relations for information retrieval [article]

Christina Lioma and Birger Larsen and Wei Lu
2017 arXiv   pre-print
We present a language model modification that considers rhetorical relations when estimating the relevance of a document to a query.  ...  Rhetorical relations, e.g. contrast, cause, explanation, describe how the parts of a text are linked to each other.  ...  [16] perform document sentiment analysis (partly) based on a document's discourse structure.  ... 
arXiv:1704.01599v1 fatcat:czpvgpcj2fgzvde2m7an3yfdnu

Predicting the Rise and Fall of Scientific Topics from Trends in their Rhetorical Framing

Vinodkumar Prabhakaran, William L. Hamilton, Dan McFarland, Dan Jurafsky
2016 Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We train topic models and a rhetorical function classifier to map topic models onto their rhetorical roles in 2.4 million abstracts from the Web of Science from 1991-2010.  ...  Computationally modeling the evolution of science by tracking how scientific topics rise and fall over time has important implications for research funding and public policy.  ...  We would also like to thank the ACL anonymous reviewers for their constructive feedback.  ... 
doi:10.18653/v1/p16-1111 dblp:conf/acl/PrabhakaranHMJ16 fatcat:fz5uh6hpbjb4lcj6zc5rsmbizm

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

Shamima Mithun, Leila Kosseim
2012 Document Numérique  
The schemata define the content and the organization of summaries based on the discourse relations present in candidate sentences.  ...  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.  ...  Acknowledgment The authors would like to thank the anonymous referees for their valuable comments. This work was financially supported by NSERC.  ... 
doi:10.3166/dn.15.2.91-120 fatcat:7yz3p7hwgnbdnek27kjchg6suy

CAST: A Cross-Article Structure Theory for Multi-Article Summarization

Nouf Ibrahim Altmami, Mohamed El Bachir Menai
2020 IEEE Access  
At the outset, these relations are classified based on the structural features of the article (that is, their appearance within each section type) and then the relations between text portions across multiple  ...  It is based on the rhetorical structure theory (RST) and the cross-document structure theory (CST). The insight that underpins CAST is to consider both intra-section and cross-section relations.  ...  ACKNOWLEDGMENT This work was supported by the Research Center of the College of Computer and Information Sciences, King Saud University. The authors are grateful for this support.  ... 
doi:10.1109/access.2020.2997881 fatcat:jbecxhopuza3vdtit5qbjtqwcy

Intentions based authoring process from audiovisual resources

Ludovic Gaillard, Jocelyne Nanard, Bruno Bachimont, Louis Chamming's
2007 Proceedings of the 2007 international workshop on Semantically aware document processing and indexing - SADPI '07  
We illustrate our approach with an example of TV news publication based on political TV archives.  ...  Our research relies on rhetorical tradition to relate author's intentions to forms and contents of target audiovisual discourse.  ...  The authors wish to thank their colleagues of the ANA team of INA: Patrick Courounet, Steffen Lalande, Claude Longerinas, for discussion and help during this work.  ... 
doi:10.1145/1283880.1283886 dblp:conf/sadpi/GaillardNBC07 fatcat:vzmui65yk5f5zg7ih5em347e6y

Exploiting Rhetorical Relations in Blog Summarization [chapter]

Shamima Mithun
2010 Lecture Notes in Computer Science  
This approach is based on the automatic identification of rhetorical predicates within candidate sentences in order to instantiate the most appropriate discourse schema and filter and order candidate sentences  ...  Concordia University, 2012 With the rapid growth of the Social Web, a large amount of informal opinionated texts are available on numerous topics.  ...  Overview of Our Schema-based Approach Given an initial question on a particular topic and a ranked list of sentences from the document set, our schema-based summarization approach identifies the most relevant  ... 
doi:10.1007/978-3-642-13059-5_53 fatcat:kltif36lsferjpgasntnna6mbi

What is this text about?

Nicolas Hernandez, Brigitte Grau
2003 Proceedings of the 21st annual international conference on Documentation - SIGDOC '03  
As most information retrieval systems return documents from an initial request made of words, a usual solution consists of presenting document titles and highlighting words of the request inside a passage  ...  In this paper, we will detail the extraction of thematic descriptors and meta-descriptors that relies on recurrence -respectively in a text or in the corpus-and how their characterization provides the  ...  SumUM, [25] , is an automatic two-steps summarizer for scientific documents based on selective text analysis.  ... 
doi:10.1145/944868.944894 dblp:conf/sigdoc/HernandezG03 fatcat:kckowxgje5bwvfo27ygjywe5xy

Multi-level mining and visualization of scientific text collections

Pablo Accuosto, Francesco Ronzano, Daniel Ferrés, Horacio Saggion
2017 Proceedings of the 6th International Workshop on Mining Scientific Publications - WOSP 2017  
The visualization components allow geographicalbased exploration of collections, topic-evolution interpretation, and collaborative network analysis among others.  ...  In addition to the extraction and enrichment of documents with metadata (titles, authors, affiliations, etc), the deep analysis performed comprises semantic interpretation, rhetorical analysis of sentences  ...  based on topic similarity.  ... 
doi:10.1145/3127526.3127529 dblp:conf/jcdl/AccuostoRFS17 fatcat:u7e5niope5conmovgpjxslk3im

Scientific knowledge object patterns

Fausto Giunchiglia, Hao Xu, Aliaksandr Birukou, Ronald Chenu
2010 Proceedings of the 15th European Conference on Pattern Languages of Programs - EuroPLoP '10  
In the past few years, a handful of discourse representation models have been proposed for the externalization of the rhetoric and argumentation captured within scientific publications.  ...  In this paper, we introduce the Scientific Knowledge Object Patterns (SKO Patterns) towards a general scientific discourse representation model, especially for managing knowledge in emerging social web  ...  James Noble, Andreas Ruping, Tim Wellhausen, James Siddle and Mandy Chessel for their detailed feedback during the workshop at Irsee.  ... 
doi:10.1145/2328909.2328928 dblp:conf/europlop/GiunchigliaXBC10 fatcat:i3tzx75kvvffhlz2y7fwpz5r3m

Ontology-based text summarization. The case of Texminer

Pedro Hípola, José A. Senso, Amed Leiva-Mederos, Sandor Domínguez-Velasco
2014 Library hi tech  
Purpose -The purpose of this paper is to look into the latest advances in ontology-based text summarization systems, with emphasis on the methodologies of a socio-cognitive approach, the structural discourse  ...  Findings -The experiment illustrates the superiority of abstracts obtained through the assistance of ontology-based techniques.  ...  Summarization systems 2.1 Linguistic techniques Summarization systems based on discourse structure analysis resort to the Rhetorical Structure Theory (RST) of Mann and Thompson (1988) to generate abstracts  ... 
doi:10.1108/lht-01-2014-0005 fatcat:yc4rve5wv5fmnlbgcjttfarbkm

Genre analysis and reading of English as a foreign language: Genre schemata beyond text typologies

Piedad Fernández Toledo
2005 Journal of Pragmatics  
The notion of genre or rhetoric schemata brings up a pragmatic dimension, and incorporates a consideration of the sociocultural conventions for the assessment of reading comprehension.  ...  This paper seeks to show the need to include the notion of genre in schema research, and more specifically in research on formal schemata.  ...  My thanks also to Rafael Monroy for reading and commenting on the second draft. I really appreciate their fruitful suggestions, and of course assume responsibility for whatever errors remain.  ... 
doi:10.1016/j.pragma.2005.01.002 fatcat:hxsdrbh2endoto2mg7in37acga

Survey of Scientific Document Summarization Techniques

Sheena Kurian K, Sheena Mathew
2020 Computer Science  
The number of scientic or research papers published every year is growing at an exponential rate, which has led to an intensive research in scientic document summarization.  ...  The different methods commonly used in automatic text summarization are discussed in this paper with their pros and cons.  ...  Rhetorical techniques depend on the logical connections between the different parts of the text.  ... 
doi:10.7494/csci.2020.21.2.3356 fatcat:mbklxkl5dfaq7ax452p3bptluq

Engineering the Production of Meta-Information: The Abstracting Concern

Maria Pinto
2003 Journal of information science  
At the level of content, three significantly different types of procedure stand out, depending on the document structure in question: extracting, rhetorical summarizing and cognitive summarizing.  ...  In order to improve the automatic production of metainformation in the abstracting field, an essential starting point is the exposition of the current state of the art.  ...  The analysis of the RS requires a rhetorical parsing algorithm based on a corpus analysis of discourse markers and text fragments.  ... 
doi:10.1177/01655515030295006 fatcat:li77lizccjh4hm43ammkqchgya
« Previous Showing results 1 — 15 out of 30,170 results