Llamipa: An Incremental Discourse Parser

Download PDF
Open Webpage

Kate Thompson, Akshay Chaturvedi, Julie Hunter, Nicholas Asher

Published: 2024, Last Modified: 07 Jan 2026EMNLP (Findings) 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
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 is able to process discourse data incrementally, which is essential for the eventual use of discourse information in downstream tasks.