Translation-Based Implicit Annotation Projection for Zero-Shot Cross-Lingual Event Argument Extraction
Authors:
Open Access
- 6 July 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2076-2081
Abstract
Zero-shot cross-lingual event argument extraction (EAE) is a challenging yet practical problem in Information Extraction. Most previous works heavily rely on external structured linguistic features, which are not easily accessible in real-world scenarios. This paper investigates a translation-based method to implicitly project annotations from the source language to the target language. With the use of translation-based parallel corpora, no additional linguistic features are required during training and inference. As a result, the proposed approach is more cost effective than previous works on zero-shot cross-lingual EAE. Moreover, our implicit annotation projection approach introduces less noises and hence is more effective and robust than explicit ones. Experimental results show that our model achieves the best performance, outperforming a number of competitive baselines. The thorough analysis further demonstrates the effectiveness of our model compared to explicit annotation projection approaches.Keywords
Funding Information
- Shenzhen Science and Technology Program (JSGG20210802154400001)
- National Natural Science Foundation of China (61876053, 62006062, 62176076)
- The Shenzhen Foundational Research Funding (JCYJ20210324115614039)
- The Joint Lab of HITSZ and China Merchants Securities
This publication has 19 references indexed in Scilit:
- Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe2017
- Neural Relation Extraction with Multi-lingual Attention2017
- Joint Event Extraction via Recurrent Neural Networks2016
- Learning to Extract Local Events from the Web2015
- Multilingual Open Relation Extraction Using Cross-lingual Projection2015
- Bilingual Active Learning for Relation Classification via Pseudo Parallel Corpora2014
- Bilingual Event Extraction: a Case Study on Trigger Type Determination2014
- The Stanford CoreNLP Natural Language Processing Toolkit2014
- Can one language bootstrap the other2009
- Concerning nonnegative matrices and doubly stochastic matricesPacific Journal of Mathematics, 1967