Deakin University
Browse

File(s) under permanent embargo

Improving Legal Information Retrieval by Distributional Composition with Term Order Probabilities

Version 2 2024-06-18, 15:04
Version 1 2023-10-24, 21:48
conference contribution
posted on 2024-06-18, 15:04 authored by Danilo S. Carvalho, Vu Tran, Khanh Van Tran, Nguyen Le Minh
Legal professionals worldwide are currently trying to get up-to-pace with the explosive growth in legal document availability through digital means. This drives a need for high efficiency Legal Information Retrieval (IR) and Question Answering (QA) methods. The IR task in particular has a set of unique challenges that invite the use of semantic motivated NLP techniques. In this work, a two-stage method for Legal Information Retrieval is proposed, combining lexical statistics and distributional sentence representations in the context of Competition on Legal Information Extraction/Entailment (COLIEE). The combination is done with the use of disambiguation rules, applied over the rankings obtained through n-gram statistics. After the ranking is done, its results are evaluated for ambiguity, and disambiguation is done if a result is decided to be unreliable for a given query. Competition and experimental results indicate small gains in overall retrieval performance using the proposed approach. Additionally, an analysis of error and improvement cases is presented for a better understanding of the contributions.

History

Volume

47

Location

London, UK

Start date

2017-06-12

End date

2017-06-13

Publication classification

E2.1 Full written paper - non-refereed / Abstract reviewed

Title of proceedings

COLIEE 2017. 4th Competition on Legal Information Extraction and Entailment

Event

COLIEE 2017. 4th Competition on Legal Information Extraction and Entailment

Publisher

EasyChair

Series

EPiC Series in Computing

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC