Applying BERT Embeddings to Predict Legal Textual Entailment

Sabine Wehnert (), Shipra Dureja, Libin Kutty, Viju Sudhi and Ernesto William Luca
Additional contact information
Sabine Wehnert: Leibniz Institute for Educational Media | Georg Eckert Institute
Shipra Dureja: Otto von Guericke University Magdeburg
Libin Kutty: Otto von Guericke University Magdeburg
Viju Sudhi: Otto von Guericke University Magdeburg
Ernesto William Luca: Leibniz Institute for Educational Media | Georg Eckert Institute

The Review of Socionetwork Strategies, 2022, vol. 16, issue 1, 197-219

Abstract: Abstract Textual entailment classification is one of the hardest tasks for the Natural Language Processing community. In particular, working on entailment with legal statutes comes with an increased difficulty, for example in terms of different abstraction levels, terminology and required domain knowledge to solve this task. In course of the COLIEE competition, we develop three approaches to classify entailment. The first approach combines Sentence-BERT embeddings with a graph neural network, while the second approach uses the domain-specific model LEGAL-BERT, further trained on the competition’s retrieval task and fine-tuned for entailment classification. The third approach involves embedding syntactic parse trees with the KERMIT encoder and using them with a BERT model. In this work, we discuss the potential of the latter technique and why of all our submissions, the LEGAL-BERT runs may have outperformed the graph-based approach.

Keywords: Contextual embeddings; Graph embeddings; Transformers; Textual entailment (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s12626-022-00101-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:trosos:v:16:y:2022:i:1:d:10.1007_s12626-022-00101-3

Ordering information: This journal article can be ordered from
https://www.springer ... ystems/journal/12626

DOI: 10.1007/s12626-022-00101-3

Access Statistics for this article

The Review of Socionetwork Strategies is currently edited by Katsutoshi Yada, Yasuharu Ukai and Marshall Van Alstyne

More articles in The Review of Socionetwork Strategies from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().