Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Cross-lingual Inference with A Chinese Entailment Graph

Publication

Cross-lingual Inference with A Chinese Entailment Graph

Li, Tianyi; Weber, Sabine; Hosseini, Mohammad Javad; u. a. (2022): Cross-lingual Inference with A Chinese Entailment Graph, in: Smaranda Muresan, Preslav Nakov, Aline Villavicencio, u. a. (Hrsg.), Findings of the Association for Computational Linguistics: ACL 2022, Association for Computational Linguistics, S. 1214–1233, doi: 10.18653/v1/2022.findings-acl.96.

Details

Faculty/Chair
Faculty/Professorship
Author
Li, Tianyi
Hosseini, Mohammad Javad
Guillou, Liane
Steedman, Mark
Title of the compilation
Findings of the Association for Computational Linguistics: ACL 2022
Editors
Muresan, Smaranda
Nakov, Preslav
Villavicencio, Aline
Conference
ACL 2022, May 2022, Dublin
Publisher Information
Association for Computational Linguistics
Year of publication
2022
Language
English
DOI
Abstract

Predicate entailment detection is a crucial task for question-answering from text, where previous work has explored unsupervised learning of entailment graphs from typed open relation triples. In this paper, we present the first pipeline for building Chinese entailment graphs, which involves a novel high-recall open relation extraction (ORE) method and the first Chinese fine-grained entity typing dataset under the FIGER type ontology. Through experiments on the Levy-Holt dataset, we verify the strength of our Chinese entailment graph, and reveal the cross-lingual complementarity: on the parallel Levy-Holt dataset, an ensemble of Chinese and English entailment graphs outperforms both monolingual graphs, and raises unsupervised SOTA by 4.7 AUC points.

Keywords
Chinese Entailment Graph
Type
Conferenceobject
URI
Activation date
2024-08-12

Permalink: https://fis.uni-bamberg.de/handle/uniba/97224 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.