Generalizing Natural Language Analysis through Span-relation Representations

Zhengbao Jiang, Wei Xu, Jun Araki, Graham Neubig


Abstract
Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple insight that a great variety of tasks can be represented in a single unified format consisting of labeling spans and relations between spans, thus a single task-independent model can be used across different tasks. We perform extensive experiments to test this insight on 10 disparate tasks spanning dependency parsing (syntax), semantic role labeling (semantics), relation extraction (information content), aspect based sentiment analysis (sentiment), and many others, achieving performance comparable to state-of-the-art specialized models. We further demonstrate benefits of multi-task learning, and also show that the proposed method makes it easy to analyze differences and similarities in how the model handles different tasks. Finally, we convert these datasets into a unified format to build a benchmark, which provides a holistic testbed for evaluating future models for generalized natural language analysis.
Anthology ID:
2020.acl-main.192
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2120–2133
Language:
URL:
https://aclanthology.org/2020.acl-main.192
DOI:
10.18653/v1/2020.acl-main.192
Bibkey:
Cite (ACL):
Zhengbao Jiang, Wei Xu, Jun Araki, and Graham Neubig. 2020. Generalizing Natural Language Analysis through Span-relation Representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2120–2133, Online. Association for Computational Linguistics.
Cite (Informal):
Generalizing Natural Language Analysis through Span-relation Representations (Jiang et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2020.acl-main.192.pdf
Video:
 http://slideslive.com/38928920
Code
 jzbjyb/SpanRel +  additional community code
Data
CoNLL-2003CoNLL-2012OIE2016Penn TreebankSemEval-2010 Task 8