An Incremental Parser for Abstract Meaning Representation
- Submitting institution
-
University of Edinburgh
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 59210369
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
- First page
- 536
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- April
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
D - Language, Interaction and Robotics
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents a novel model for performing semantic parsing using Abstract Meaning Representation (AMR) - a fundamental problem in Natural Language Processing which aims at resolving "who did what to who" in text. The empirical results presented were comparable to state of the art. An important contribution of this paper is a suite of evaluation metrics for AMR parsing. This suite has become the standard in evaluating AMR parsers, and has significantly influenced the way AMR parsers are evaluated. This paper led to several follow-up papers, including about cross-lingual semantic parsing and text generation from AMR, challenging, important problems.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -