Linking discourse-level information and the induction of bilingual discourse connective lexicons

Download

index.pdf

Date

2022-6-20

Author

Özer, Sibel
Kurfall, Murathan
Zeyrek Bozşahin, Deniz
Mendes, Amália
Oleškevičiene, Giedre Valunaite

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

191
views

66
downloads

The single biggest obstacle in performing comprehensive cross-lingual discourse analysis is the scarcity of multilingual resources. The existing resources are overwhelmingly monolingual, compelling researchers to infer the discourse-level information in the target languages through error-prone automatic means. The current paper aims to provide a more direct insight into the cross-lingual variations in discourse structures by linking the annotated relations of the TED-Multilingual Discourse Bank, which consists of independently annotated six TED talks in seven different languages. It is shown that the linguistic labels over the relations annotated in the texts of these languages can be automatically linked with English with high accuracy, as verified against the relations of three diverse languages semi-automatically linked with relations over English texts. The resulting corpus has a great potential to reveal the divergences in local discourse relations, as well as leading to new resources, as exemplified by the induction of bilingual discourse connective lexicons.

Subject Keywords

Discourse relations, discourse connectives, discourse connective lexicons, linking discourse relations, parallel corpus, discourse connective lexicons, discourse connectives, Discourse relations, linking discourse relations, parallel corpus

URI

https://hdl.handle.net/11511/101845

Journal

Semantic Web

DOI

https://doi.org/10.3233/sw-223011

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

Automatic disambiguation of Turkish discourse connectives based on a Turkish connective lexicon Başıbüyük, Kezban; Doğru, Ali Hikmet; Zeyrek Bozşahin, Deniz; Department of Computer Engineering (2021-8-31) In this thesis, we developed methods for disambiguating the discourse usage and sense of connectives in a given free Turkish text. For this purpose, we firstly built a comprehensive Turkish Connective Lexicon (TCL) including all types of connectives in Turkish together with their syntactic and semantic features. This lexicon is built automatically by using the discourse relation annotations in several discourse annotated corpora developed for Turkish and follows the format of the German connective lexicon, ...
Usage disambiguation of Turkish discourse connectives Başıbüyük, Kezban; Zeyrek Bozşahin, Deniz (2023-01-01) This paper describes a rule-based approach and a machine learning approach to disambiguate the discourse usage of Turkish connectives, which not only has single and phrasal connectives as most languages do, but also suffixal connectives that largely correspond to subordinating conjunctions in English. Since these connectives have different linguistic characteristics, two sets of linguistic rules are devised to disambiguate their discourse usage. The linguistic rules are used in the rule-based approach and e...
An Exploratory Analysis of TED Talks in English and Lithuanian, Portuguese and Turkish Translations Zeyrek Bozşahin, Deniz; Mendes, Amália; Oleškevičienė, Giedrė Valūnaitė; Özer, Sibel (2022-1-01) This paper contributes to the question of how discourse relations are realised in TED talks. Drawing on an annotated, multilingual discourse corpus of TED talk transcripts, we examine discourse relations in English and Lithuanian, Portuguese and Turkish translations by concentrating on three aspects: The degree of explicitness in discourse relations, the extent to which explicit and implicit relations are encoded inter-or intra-sententially, and whether top-level discourse relation senses employed in Englis...
National social dialogue structures and the european employment strategy: comparing Greece and Ireland Cihan, Gizem; Yalman, Osman Galip; Tsarouhas, Dimitri; Department of European Studies (2010) The purpose of this thesis is to analyse the impact of European Employment Strategy (EES) on social partnership at national level. Increasing the participation of trade unions, employer organisations and other social partners in policy formulation and implementation is one of the EES objectives. A comparative study has been conducted on Ireland and Greece in order to analyse to what extent this objective has been achieved through EES, which is an Open Method of Coordination. Historical institutionalism prov...
The aspects of Central Asian economic integration after 1991: the reasons of inefficiency Manasov, Zamirbek; Şen, Mustafa; Department of Eurasian Studies (2008) This study seeks to analyze the dimensions of economic integration in the Central Asia after the independence. The collapse of the Soviet Union opened new perspectives for Central Asian states and gave chance to follow national policies independently. However, used to be parts of the big economic complex of the former Soviet Union and being lack of government experience in public and private economy made them to cooperate with old and new markets. The study argues that although there were established number...

Citation Formats

S. Özer, M. Kurfall, D. Zeyrek Bozşahin, A. Mendes, and G. V. Oleškevičiene, “Linking discourse-level information and the induction of bilingual discourse connective lexicons,” Semantic Web, vol. 13, no. 6, pp. 1081–1102, 2022, Accessed: 00, 2023. [Online]. Available: https://hdl.handle.net/11511/101845.