HomeLREC 2026WorkshopsSLIDElrec2026-ws-slide-15
Back to SLIDE 2026
LREC 2026workshop

Using syntax for the semantic representation of sentences

Proceedings of the Workshop on Structured Linguistic Data and Evaluation (SLiDE)

DOI:10.63317/4gtinxarm3dd

Abstract

Deep learning methods in natural language processing often rely on statistical methods to tokenize texts before vectorization. This segmentation produces lexical subunits offering great flexibility. However, the reuse of identical tokens across words with different meanings can favor representations based on surface form rather than on linguistic information, especially semantics. This mismatch between semantics and surface form can lead to undesirable effects in language processing. To limit the influence of form on the semantics of vector representations, we propose an intermediate representation based on syntactic parsing that is more compact and more faithful to word meaning.

Details

Paper ID
lrec2026-ws-slide-15
Pages
pp. 169-179
BibKey
boucharenc-etal-2026-syntax
Editors
Germany) Erhard Hinrichs (Tübingen University, Sweden) Joakim Nivre (Uppsala University, Bulgaria) Petya Osenova (Sofia University, USA) James Pustejovsky (Brandeis University, Germany) Claus Zinn (Tübingen University
Publisher
European Language Resources Association (ELRA)
ISSN
N/A
ISBN
N/A
Workshop
Proceedings of the Workshop on Structured Linguistic Data and Evaluation (SLiDE)
Location
Palma, Mallorca, Spain
Date
11 - 16 May 2026

Authors

  • IB

    Iskandar Boucharenc

  • ES

    Eve Sauvage

  • TG

    Thomas Gerald

  • JT

    Julien Tourille

  • SC

    Sabrina Campano

  • CG

    Cyril Grouin

  • SR

    Sophie Rosset

Links