Llamipa: An Incremental Discourse Parser

Kate Thompson, Akshay Chaturvedi, Julie Hunter, Nicholas Asher
6/26/2024
cs.CL

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Can we obtain significant success in RST discourse parsing by using Large Language Models?

83% match1 repo192024

BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models

80% match2025

CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversations

79% match1 repo12025

A Fully Automated Pipeline for Conversational Discourse Annotation: Tree Scheme Generation and Labeling with Large Language Models

79% match2025

Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set

78% match1 repo2025

Llama-Mimi: Speech Language Models with Interleaved Semantic and Acoustic Tokens

78% match2025

Cite this paper

@article{thompson2024llamipa,
  title  = {Llamipa: An Incremental Discourse Parser},
  author = {Kate Thompson and Akshay Chaturvedi and Julie Hunter and Nicholas Asher},
  year   = {2024},
  eprint = {2406.18256},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.18256v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.18256.svg)](https://codeofpaper.com/paper/2406.18256)

Discussion