| アイテムタイプ |
会議発表論文 / Conference Paper(1) |
| 公開日 |
2025-07-16 |
| タイトル |
|
|
タイトル |
Can we obtain significant success in RST discourse parsing by using Large Language Models? |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ |
conference paper |
| アクセス権 |
|
|
アクセス権 |
open access |
| 著者 |
Maekawa, Aru
Hirao, Tsutomu
上垣外, 英剛
Okumura, Manabu
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Recently, decoder-only pre-trained large language models (LLMs), with several tens of billion parameters, have significantly impacted a wide range of natural language processing (NLP) tasks. While encoder-only or encoder-decoder pre-trained language models have already proved to be effective in discourse parsing, the extent to which LLMs can perform this task remains an open research question. Therefore, this paper explores how beneficial such LLMs are for Rhetorical Structure Theory (RST) discourse parsing. Here, the parsing process for both fundamental top-down and bottom-up strategies is converted into prompts, which LLMs can work with. We employ Llama 2 and fine-tune it with QLoRA, which has fewer parameters that can be tuned. Experimental results on three benchmark datasets, RST-DT, Instr-DT, and the GUM corpus, demonstrate that Llama 2 with 70 billion parameters in the bottom-up strategy obtained state-of-the-art (SOTA) results with significant differences. Furthermore, our parsers demonstrated generalizability when evaluated on RST-DT, showing that, in spite of being trained with the GUM corpus, it obtained similar performances to those of existing parsers trained with RST-DT. |
| 書誌情報 |
en : Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL2024)
巻 1,
p. 2803-2815,
ページ数 13,
発行日 2024-03
|
| 会議情報 |
|
|
|
会議名 |
The 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL2024) |
|
|
開始年 |
2024 |
|
|
開始月 |
03 |
|
|
開始日 |
17 |
|
|
終了年 |
2024 |
|
|
終了月 |
03 |
|
|
終了日 |
22 |
|
|
開催期間 |
2024-03-17 - 2024-03-22 |
|
|
開催地 |
St. Julian’s, Malta |
|
開催国 |
MLT |
| 出版者 |
|
|
出版者 |
Association for Computational Linguistics |
| 出版者版URI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://aclanthology.org/2024.eacl-long.171/ |
| 権利 |
|
|
権利情報Resource |
https://creativecommons.org/licenses/by/4.0/ |
|
権利情報 |
$00A9 2024 Association for Computational Linguistics. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License. |
| 著者版フラグ |
|
|
出版タイプ |
NA |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
21H03505 |
|
|
研究課題名 |
動画談話構造解析とそれを用いた要約生成 |
