Categorizing comparative sentences

Alexander Panchenko, Alexander Bondarenko, Mirco Franzek, Matthias Hagen, Chris Biemann

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

11 Citations (SciVal)

Abstract

We tackle the tasks of automatically identifying comparative sentences and categorizing the intended preference (e.g., "Python has better NLP libraries than MATLAB" ! Python, better, MATLAB). To this end, we manually annotate 7,199 sentences for 217 distinct target item pairs from several domains (27% of the sentences contain an oriented comparison in the sense of "better" or "worse"). A gradient boosting model based on pre-trained sentence embeddings reaches an F1 score of 85% in our experimental evaluation. The model can be used to extract comparative sentences for pro/con argumentation in comparative / argument search engines or debating technologies.

Original languageEnglish
Title of host publicationACL 2019 - 6th Workshop on Argument Mining, ArgMining 2019 - Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages136-145
Number of pages10
ISBN (Electronic)9781950737338
Publication statusPublished - 2019
Event6th Workshop on Argument Mining, ArgMining 2019, collocated with ACL 2019 - Florence, Italy
Duration: 1 Aug 2019 → …

Publication series

NameACL 2019 - 6th Workshop on Argument Mining, ArgMining 2019 - Proceedings of the Workshop

Conference

Conference6th Workshop on Argument Mining, ArgMining 2019, collocated with ACL 2019
Country/TerritoryItaly
CityFlorence
Period1/08/19 → …

Fingerprint

Dive into the research topics of 'Categorizing comparative sentences'. Together they form a unique fingerprint.

Cite this