Document-Level Event Argument Extraction by Conditional Generation

04/13/2021
by   Sha Li, et al.
0

Event extraction has long been treated as a sentence-level task in the IE community. We argue that this setting does not match human information-seeking behavior and leads to incomplete and uninformative extraction results. We propose a document-level neural event argument extraction model by formulating the task as conditional generation following event templates. We also compile a new document-level event extraction benchmark dataset WikiEvents which includes complete event and coreference annotation. On the task of argument extraction, we achieve an absolute gain of 7.6 the RAMS and WikiEvents datasets respectively. On the more challenging task of informative argument extraction, which requires implicit coreference reasoning, we achieve a 9.3 portability of our model, we also create the first end-to-end zero-shot event extraction framework and achieve 97 extraction performance and 82 only access to 10 out of the 33 types on ACE.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/06/2022

Few-Shot Document-Level Event Argument Extraction

Event argument extraction (EAE) has been well studied at the sentence le...
research
05/13/2020

Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding

Few works in the literature of event extraction have gone beyond individ...
research
10/01/2021

Learning to Ask for Data-Efficient Event Argument Extraction

Event argument extraction (EAE) is an important task for information ext...
research
08/16/2022

DICE: Data-Efficient Clinical Event Extraction with Generative Models

Event extraction in the clinical domain is an under-explored research ar...
research
09/18/2022

Dynamic Global Memory for Document-level Argument Extraction

Extracting informative arguments of events from news articles is a chall...
research
04/06/2022

Improving Zero-Shot Event Extraction via Sentence Simplification

The success of sites such as ACLED and Our World in Data have demonstrat...
research
12/11/2021

Efficient Document-level Event Extraction via Pseudo-Trigger-aware Pruned Complete Graph

There are two main challenges in document-level event extraction: 1) arg...

Please sign up or login with your details

Forgot password? Click here to reset