Conference proceeding
Label Definitions Improve Semantic Role Labeling
NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, pp 5613-5620
01 Jan 2022
Abstract
Argument classification is at the core of Semantic Role Labeling. Given a sentence and the predicate, a semantic role label is assigned to each argument of the predicate. While semantic roles come with meaningful definitions, existing work has treated them as symbolic. Learning symbolic labels usually requires ample training data, which is frequently unavailable due to the cost of annotation. We instead propose to retrieve and leverage the definitions of these labels from the annotation guidelines. For example, the verb predicate "work" has arguments defined as "worker", "job", "employer", etc. Our model achieves state-of-theart performance on the CoNLL09 English SRL dataset injected with label definitions given the predicate senses. The performance improvement is even more pronounced in low-resource settings when training data is scarce.(1)
Metrics
Details
- Title
- Label Definitions Improve Semantic Role Labeling
- Creators
- Li Zhang - University of PennsylvaniaIshan Jindal - IBM Research (China)Yunyao Li - IBM Research (China)
- Publication Details
- NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, pp 5613-5620
- Publisher
- Association of Computational Linguistics
- Number of pages
- 8
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:000859869505053
- Other Identifier
- 991022123446104721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Industry collaboration
- Domestic collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Interdisciplinary Applications
- Linguistics