Event Extraction by Answering (Almost) Natural Questions

Xinya Du, Claire Cardie
4/28/2020
cs.CL

Official code: xinyadu/eeqa (206 stars, MIT, last commit 2022-10-04).

Abstract

The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments. Existing work in event argument extraction typically relies heavily on entity recognition as a preprocessing/concurrent step, causing the well-known problem of error propagation. To avoid this issue, we introduce a new paradigm for event extraction by formulating it as a question answering (QA) task that extracts the event arguments in an end-to-end manner. Empirical results demonstrate that our framework outperforms prior methods substantially; in addition, it is capable of extracting event arguments for roles not seen at training time (zero-shot learning setting).

View on arXivView PDF

Code Implementations(1)

xinyadu/eeqaOfficial100%
MIT

Event Extraction by Answering (Almost) Natural Questions

20650Shell, PythonAug 25, 20204 years agoMIT

Similar Papers

Asking and Answering Questions to Extract Event-Argument Structures

84% match2024

Token-Event-Role Structure-based Multi-Channel Document-Level Event Extraction

84% match2023

Utilizing Contextual Clues and Role Correlations for Enhancing Document-level Event Argument Extraction

82% match2023

Joint Event Extraction via Structural Semantic Matching

82% match2023

A Multimodal Text- and Graph-Based Approach for Open-Domain Event Extraction from Documents

82% match2026

ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT

81% match1 repo8252023

Cite this paper

@article{du2020event,
  title  = {Event Extraction by Answering (Almost) Natural Questions},
  author = {Xinya Du and Claire Cardie},
  year   = {2020},
  eprint = {2004.13625},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2004.13625}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2004.13625.svg)](https://codeofpaper.com/paper/2004.13625)

Discussion