Prompt for extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction

In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes prompt tuning for extractive objectives to take the best advan...

Full description

Saved in:
Bibliographic Details
Main Authors: MA, Yubo, WANG, Zehao, CAO, Yixin, LI, Mukai, CHEN, Meiqi, WANG, Kun, SHAO, Jing
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7447
https://ink.library.smu.edu.sg/context/sis_research/article/8450/viewcontent/2022.acl_long.466.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8450
record_format dspace
spelling sg-smu-ink.sis_research-84502022-10-20T07:33:31Z Prompt for extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction MA, Yubo WANG, Zehao CAO, Yixin LI, Mukai CHEN, Meiqi WANG, Kun SHAO, Jing In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes prompt tuning for extractive objectives to take the best advantages of Pre-trained Language Models (PLMs). It introduces two span selectors based on the prompt to select start/end tokens among input texts for each role. On the other hand, it captures argument interactions via multi-role prompts and conducts joint optimization with optimal span assignments via a bipartite matching loss. Also, with a flexible prompt design, PAIE can extract multiple arguments with the same role instead of conventional heuristic threshold tuning. We have conducted extensive experiments on three benchmarks, including both sentenceand document-level EAE. The results present promising improvements from PAIE (3.5% and 2.3% F1 gains in average on three benchmarks, for PAIE-base and PAIE-large respectively). Further analysis demonstrates the efficiency, generalization to few-shot settings, and effectiveness of different extractive prompt tuning strategies. Our code is available at https: //github.com/mayubo2333/PAIE. 2022-05-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7447 info:doi/10.18653/v1/2022.acl-long.466 https://ink.library.smu.edu.sg/context/sis_research/article/8450/viewcontent/2022.acl_long.466.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
Graphics and Human Computer Interfaces
spellingShingle Databases and Information Systems
Graphics and Human Computer Interfaces
MA, Yubo
WANG, Zehao
CAO, Yixin
LI, Mukai
CHEN, Meiqi
WANG, Kun
SHAO, Jing
Prompt for extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
description In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes prompt tuning for extractive objectives to take the best advantages of Pre-trained Language Models (PLMs). It introduces two span selectors based on the prompt to select start/end tokens among input texts for each role. On the other hand, it captures argument interactions via multi-role prompts and conducts joint optimization with optimal span assignments via a bipartite matching loss. Also, with a flexible prompt design, PAIE can extract multiple arguments with the same role instead of conventional heuristic threshold tuning. We have conducted extensive experiments on three benchmarks, including both sentenceand document-level EAE. The results present promising improvements from PAIE (3.5% and 2.3% F1 gains in average on three benchmarks, for PAIE-base and PAIE-large respectively). Further analysis demonstrates the efficiency, generalization to few-shot settings, and effectiveness of different extractive prompt tuning strategies. Our code is available at https: //github.com/mayubo2333/PAIE.
format text
author MA, Yubo
WANG, Zehao
CAO, Yixin
LI, Mukai
CHEN, Meiqi
WANG, Kun
SHAO, Jing
author_facet MA, Yubo
WANG, Zehao
CAO, Yixin
LI, Mukai
CHEN, Meiqi
WANG, Kun
SHAO, Jing
author_sort MA, Yubo
title Prompt for extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
title_short Prompt for extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
title_full Prompt for extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
title_fullStr Prompt for extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
title_full_unstemmed Prompt for extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
title_sort prompt for extraction? paie: prompting argument interaction for event argument extraction
publisher Institutional Knowledge at Singapore Management University
publishDate 2022
url https://ink.library.smu.edu.sg/sis_research/7447
https://ink.library.smu.edu.sg/context/sis_research/article/8450/viewcontent/2022.acl_long.466.pdf
_version_ 1770576350861590528