Deakin University
Browse

File(s) under permanent embargo

Learning parse-free event-based features for textual entailment recognition

conference contribution
posted on 2010-01-01, 00:00 authored by Bahadorreza OfoghiBahadorreza Ofoghi, John YearwoodJohn Yearwood
We propose new parse-free event-based features to be used in conjunction with lexical, syntactic, and semantic features of texts and hypotheses for Machine Learning-based Recognizing Textual Entailment. Our new similarity features are extracted without using shallow semantic parsers, but still lexical and compositional semantics are not left out. Our experimental results demonstrate that these features can improve the effectiveness of the identification of entailment and no-entailment relationships.

History

Volume

6464

Pagination

184-193

Location

Adelaide, S. Aust.

Start date

2010-10-07

End date

2010-10-10

ISBN-13

978-3-642-17431-5

ISBN-10

3642174310

Language

eng

Publication classification

E1.1 Full written paper - refereed, E Conference publication

Copyright notice

2010, Springer-Verlag Berlin Heidelberg

Title of proceedings

AI 2010 : Proceedings of the 23rd Australasian Joint Conference on Artificial Intelligence

Event

Australian Computer Society National Committee for Artificial Intelligence. Conference (23rd : 2010 : Adelaide, S. Aust.)

Publisher

Springer

Place of publication

Berlin, Germany

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC