Llamipa: An Incremental Discourse Parser

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thompson, Kate, Chaturvedi, Akshay, Hunter, Julie, Asher, Nicholas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909333507276800
author Thompson, Kate
Chaturvedi, Akshay
Hunter, Julie
Asher, Nicholas
author_facet Thompson, Kate
Chaturvedi, Akshay
Hunter, Julie
Asher, Nicholas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18256
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Llamipa: An Incremental Discourse Parser
Thompson, Kate
Chaturvedi, Akshay
Hunter, Julie
Asher, Nicholas
Computation and Language
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.
title Llamipa: An Incremental Discourse Parser
topic Computation and Language
url https://arxiv.org/abs/2406.18256