Llamipa: An Incremental Discourse Parser - Intelligence Artificielle
Conference Papers Year : 2024

Llamipa: An Incremental Discourse Parser

Abstract

This paper provides the first discourse parsing experiments with a large language model (LLM) finetuned on corpora annotated in the style of SDRT (Segmented Discourse Representation Theory Asher, 1993; Asher and Lascarides, 2003). The result is a discourse parser, Llamipa (Llama Incremental Parser), that leverages discourse context, leading to substantial performance gains over approaches that use encoder-only models to provide local, context-sensitive representations of discourse units. Furthermore, it can process discourse data incrementally, which is essential for the eventual use of discourse information in downstream tasks.

Fichier principal
Vignette du fichier
llamipa-1.pdf (738.77 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04829235 , version 1 (10-12-2024)

Licence

Identifiers

  • HAL Id : hal-04829235 , version 1

Cite

Kate Thompson, Akshay Chaturvedi, Julie Hunter, Nicholas Asher. Llamipa: An Incremental Discourse Parser. EMNLP 2024, ACL, Nov 2024, Miami (FL), United States. pp.6418-6430. ⟨hal-04829235⟩
0 View
0 Download

Share

More