Llamipa: An Incremental Discourse Parser
This provides an incremental discourse parser for natural language processing applications, though it is an incremental improvement using existing methods on new data.
The paper tackles discourse parsing by fine-tuning a large language model on SDRT-annotated corpora, resulting in Llamipa which achieves substantial performance gains over encoder-only models and enables incremental processing.
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.