<abstract xmlns="http://www.w3.org/1999/xhtml"><p>This paper presents a supervised approach to the recognition of Cross-document Structure Theory (CST) relations in Polish texts. Its core is a graph-based 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.</p></abstract>

This paper presents a supervised approach to the recognition of Cross-document Structure Theory (CST) relations in Polish texts. Its core is a graph-based 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.

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

Wrocław University of Science and Technology

Cybernetics and Information Technologies

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

This paper presents a supervised approach to the recognition of Cross-document Structure Theory (CST) relations in Polish texts. Its core is a graph-based...

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

Data publikacji: 30 mar 2018

Zakres stron: 152 - 170

Otrzymano: 20 paź 2017

Przyjęty: 31 sty 2018

DOI: https://doi.org/10.2478/cait-2018-0013

Słowa kluczowe
Cross-document structure theory, CST, supervised learning, graph-based representation, logistic model tree, LMT, support vector machine, SVM

© 2018 Arkadiusz Janz et al., published by De Gruyter Open

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

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

Data publikacji: 30 mar 2018

Zakres stron: 152 - 170

Otrzymano: 20 paź 2017

Przyjęty: 31 sty 2018

DOI: https://doi.org/10.2478/cait-2018-0013

Słowa kluczoweCross-document structure theory, CST, supervised learning, graph-based representation, logistic model tree, LMT, support vector machine, SVM

© 2018 Arkadiusz Janz et al., published by De Gruyter Open

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Słowa kluczowe
Cross-document structure theory, CST, supervised learning, graph-based representation, logistic model tree, LMT, support vector machine, SVM