Revisiting Cross-document Structure Theory for multi-document discourse parsing

Maziero, Erick Galani; Jorge, Maria Lucía del Rosario Castro; Pardo, Thiago Alexandre Salgueiro

doi:10.1016/j.ipm.2013.12.003

Cited by 7 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the ambiguity in the interpretation of certain CST relationships M a z i e r o, J o r g e and P a r d o [22] proposed several refinements to CST in order to reduce the ambiguity. They improved definitions by introducing several additional constraints on the co-occurrence of different relations in texts.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Graph-Based Complex Representation in Inter-Sentence Relation Recognition in Polish Texts

Janz

Kędzia

Piasecki

2018

Cybernetics and Information Technologies

View full text Add to dashboard Cite

This paper presents a supervised approach to the recognition of Crossdocument Structure Theory (CST) relations in Polish texts. Its core is a graphbased representation constructed for sentences. Graphs are built on the basis of lexicalised syntactic-semantic relations extracted from text. Similarity between sentences is calculated as similarity between their graphs, and the values are used as features to train the classifiers. Several different configurations of graphs, as well as graph similarity methods were analysed for this task. The approach was evaluated on a large open corpus annotated manually with 17 types of selected CST relations. The configuration of experiments was similar to those known from SEMEVAL and we obtained very promising results.

show abstract

Section: Related Workmentioning

confidence: 99%

“…As a starting point for the selection of features describing sentence pairs we used the set features proposed by M a z i e r o, J o r g e and P a r d o [22]. Our set includes commonly-used, lexical, syntactic and semantic features that were applied for the detection and recognition of CST relationships in supervised approaches.…”

Section: Baseline Featuresmentioning

confidence: 99%

Graph-Based Complex Representation in Inter-Sentence Relation Recognition in Polish Texts

Janz

Kędzia

Piasecki

2018

Cybernetics and Information Technologies

View full text Add to dashboard Cite

show abstract

“…The author proposed 24 CST relations, however, in this study we consider only 14 relations found in the corpus we use in our evaluation (see Section 4). Such relations are organized in a typology defined in [35] [36]. This typology is shown in Figure 5.…”

Section: Cross-document Structure Theorymentioning

confidence: 99%

“…Based on the meaning of the relationships defined in [35,36], these may assist in the clustering phase, in order to obtain a better selection of similar subtopics. This is due to the fact that it was found in previous work that the discourse relations are closely related to the lexical similarity of textual segments, i.e., the closer such segments are, the more CST relationships they have with each other and, therefore, the greater the chance is that the segments belong to the same subtopic.…”

Section: Cross-document Structure Theorymentioning

confidence: 99%

“…The automatic annotation, in turn, is performed by discourse parsers, which are softwares that automatically detect relationships among segments of texts and build graphs with the resulting annotation. For Portuguese, it is available a discourse parser for CST called CSTParser [35,36], with a general accuracy of 68%. In this paper, we have used the manual annotation already available in our corpus, but, if one desires, the method may be scalable to new texts by using the available discourse parser.…”

Section: Cross-document Structure Theorymentioning

confidence: 99%

See 1 more Smart Citation

Exploring the subtopic-based relationship map strategy for multi-document summarization

Ribaldo

Cardoso²,

Pardo³

2016

RITA

View full text Add to dashboard Cite

Neste artigo, foi adaptada e explorada uma estratégia de geração de sumários multidocumento com base na abordagem de mapas de relacionamento, a qual representa textos como grafos (mapas) de segmentos inter-relacionados e aplica técnicas de percurso em grafo para produzir os sumários. Em particular, utilizou-se o Caminho Denso-Segmentado, um método sofisticado que tenta representar em um sumário os principais subtópicos dos textos de origem, mantendo a informatividade do sumário. Além disso, também foram investigadas algumas técnicas de segmentação e agrupamento de subtópicos bem conhecidas, a fim de selecionar corretamente as informações mais relevantes para compor o sumário final. Mostra-se que este método de sumarização baseado em subtópicos supera outros métodos de sumarização multidocumento e atinge resultados do estado da arte, competindo com os métodos de sumarização profundos mais sofisticados da área. Explorando mapas de relacionamento com base em subtópicos para sumarização multidocumento Abstract: In this paper we adapt and explore a strategy for generating multidocument summaries based on the relationship map approach, which represent texts as graphs (maps of interrelated segments and apply traversing techniques for producing the summaries. In particular, we work on the Segmented Bushy Path, a sophisticated method which tries to represent in a summary the main subtopics from the source texts while keeping its informativeness. In addition, we also investigate some well-known subtopic segmentation and clustering techniques in order to correctly select the most relevant information to compose the final summary. We show that this subtopic-based summarization method outperforms other methods for multi-document summarization and achieves state of the art results, competing with the most sophisticated deep summarization methods in the area.

show abstract

Exploring the Potentiality of Semantic Features for Paraphrase Detection

Anchiêta

Pardo

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Revisiting Cross-document Structure Theory for multi-document discourse parsing

Cited by 7 publications

References 16 publications

Graph-Based Complex Representation in Inter-Sentence Relation Recognition in Polish Texts

Graph-Based Complex Representation in Inter-Sentence Relation Recognition in Polish Texts

Exploring the subtopic-based relationship map strategy for multi-document summarization

Exploring the Potentiality of Semantic Features for Paraphrase Detection

Contact Info

Product

Resources

About