Language modeling for legal proof

Le Cheng, Winnie Cheng

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

7 Citations (Scopus)

Abstract

In common law jurisdictions, the notion of proof beyond a reasonable doubt is frequently related to notions such as the belief or certainty of a judge or a juror about reality. The notion of balance of probabilities is however related to likelihood or probability. In this analysis, we link belief and proof by introducing the notion of epistemic modality, which is concerned with speaker's belief in propositional probability. The variation in the orientation of epistemic modality helps to integrate the two levels of proof and bridge the apparent test gap between them. The analysis further introduces the notion of relevance in order to clarify the nature of legal proof by taking rape cases as example. This analysis then provides an integrated language model to improve but diversify the expressions in terms of burden of proof.
Original languageEnglish
Title of host publicationProceedings of 2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2010
Pages533-537
Number of pages5
DOIs
Publication statusPublished - 1 Dec 2010
Event2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2010 - Hangzhou, China
Duration: 15 Nov 201016 Nov 2010

Conference

Conference2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2010
Country/TerritoryChina
CityHangzhou
Period15/11/1016/11/10

Keywords

  • Belief
  • Language modeling
  • Legal proof
  • Modality
  • Probability
  • Relevance

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems

Fingerprint

Dive into the research topics of 'Language modeling for legal proof'. Together they form a unique fingerprint.

Cite this