Construction and Alignment of Multilingual Entailment Graphs for Semantic Inference

Sabine Weber, Mark Steedman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents ongoing work on the construction and alignment of predicate entailment graphs in English and German. We extract predicate-argument pairs from large corpora of monolingual English and German news text and construct monolingual paraphrase clusters and entailment graphs. We use an aligned subset of entities to derive the bilingual alignment of entities and relations, and achieve better than baseline results on a translated subset of a predicate entailment data set (Levy and Dagan, 2016) and the German portion of XNLI (Conneau et al., 2018).
Original languageEnglish
Title of host publicationProceedings of the 2019 Workshop on Widening NLP
Place of PublicationFlorence, Italy
PublisherAssociation for Computational Linguistics
Pages77-79
Number of pages3
ISBN (Print)978-1-950737-42-0
Publication statusPublished - 1 Aug 2019
EventWidening Natural Language Processing Workshop 2019 - Florence, Italy
Duration: 28 Jul 201928 Jul 2019
http://www.winlp.org/winlp-2019-workshop/

Workshop

WorkshopWidening Natural Language Processing Workshop 2019
Abbreviated titleWiNLP 2019
Country/TerritoryItaly
CityFlorence
Period28/07/1928/07/19
Internet address

Fingerprint

Dive into the research topics of 'Construction and Alignment of Multilingual Entailment Graphs for Semantic Inference'. Together they form a unique fingerprint.

Cite this