Smoothing Entailment Graphs with Language Models

Nick McKenna, Tianyi Li, Mark Johnson, Mark Steedman

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

Abstract / Description of output

The diversity and Zipfian frequency distribution of natural language predicates in corpora leads to sparsity in Entailment Graphs (EGs) built by Open Relation Extraction (ORE). EGs are computationally efficient and explainable models of natural language inference, but as symbolic models, they fail if a novel premise or hypothesis vertex is missing at test-time. We present theory and methodology for overcoming such sparsity in symbolic models. First, we introduce a theory of optimal smoothing of EGs by constructing transitive chains. We then demonstrate an efficient, open-domain, and unsupervised smoothing method using an off-the-shelf Language Model to find approximations of missing premise predicates. This improves recall by 25.1 and 16.3 percentage points on two difficult directional entailment datasets, while raising average precision and maintaining model explainability. Further, in a QA task we show that EG smoothing is most useful for answering questions with lesser supporting text, where missing premise predicates are more costly. Finally, controlled experiments with WordNet confirm our theory and show that hypothesis smoothing is difficult, but possible in principle.
Original languageEnglish
Title of host publicationProceedings of the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL/IJCNLP)
PublisherAssociation for Computational Linguistics (ACL)
Pages551-563
Number of pages13
Volume1
ISBN (Electronic)979-8-89176-013-4
Publication statusPublished - 1 Nov 2023
EventThe 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics - Bali, Indonesia
Duration: 1 Nov 20234 Nov 2023
http://www.ijcnlp-aacl2023.org/

Conference

ConferenceThe 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
Abbreviated titleIJCNLP-AACL 2023
Country/TerritoryIndonesia
CityBali
Period1/11/234/11/23
Internet address

Fingerprint

Dive into the research topics of 'Smoothing Entailment Graphs with Language Models'. Together they form a unique fingerprint.

Cite this