paper-with-me

홈 › Papers

Llamipa: An Incremental Discourse Parser

2024-06-26 · Kate Thompson, Akshay Chaturvedi, Julie Hunter, Nicholas Asher

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.

📄 PDF Abstract BibTeX arXiv:2406.18256

Code (0)

등록된 구현이 없습니다.

Tasks

Discourse ParsingLanguage ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Beyond Supervised Clarification: Input Rewriting with LLMs for Dialogue Discourse Parsing

2026-07-02 · Yiming Liu, Ziyue Zhang, Zhichao Xu, Xin Yu 외 arxiv

Rewriting inputs to improve frozen downstream models has become a common strategy in modern NLP pipelines. Prior work on incremental dialogue discourse parsing (DDP) shows that supervised clarification models can rewrite…

Discourse Parsing

Persian Rhetorical Structure Theory

2021-06-25 · Sara Shahmohammadi, Hadi Veisi, Ali Darzi

Over the past years, interest in discourse analysis and discourse parsing has steadily grown, and many discourse-annotated corpora and, as a result, discourse parsers have been built. In this paper, we present a discours…

Discourse Parsing

Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank

2017-08-28 · EMNLP 2017 9 · Kai Zhao, Liang Huang

Discourse parsing has long been treated as a stand-alone problem independent from constituency or dependency parsing. Most attempts at this problem are pipelined rather than end-to-end, sophisticated, and not self-contai…

Dependency ParsingDiscourse Parsing

A Complete Shift-Reduce Chinese Discourse Parser with Robust Dynamic Oracle

2020-07-01 · ACL 2020 6 · Shyh-Shiun Hung, Hen-Hsen Huang, Hsin-Hsi Chen

This work proposes a standalone, complete Chinese discourse parser for practical applications. We approach Chinese discourse parsing from a variety of aspects and improve the shift-reduce parser not only by integrating t…

Data AugmentationDiscourse Parsing

Unsupervised Discourse Constituency Parsing Using Viterbi EM

2020-01-01 · TACL 2020 1 · Noriki Nishida, Hideki Nakayama

In this paper, we introduce an unsupervised discourse constituency parsing algorithm. We use Viterbi EM with a margin-based criterion to train a span-based discourse parser in an unsupervised manner. We also propose init…

Constituency ParsingDiscourse Parsing