End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories
- Submitting institution
-
The University of Sheffield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 5240
- Type
- E - Conference contribution
- DOI
-
10.18653/v1/P19-1378
- Title of conference / published proceedings
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- First page
- 3888
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- July
- Year of publication
- 2019
- 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 - Natural Language Processing
- Citation count
- 10
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- First work to use linguistic theories to directly inform the design of Deep Neural Networks for end-to-end sequential metaphor identification, advancing the state-of-the-art. This work was published in ACL, the premier computational linguistics conference, and has led to collaboration with Peking University, China (contact: research staff). Amazon identified and offer a position to the first author, Lin’s PhD student, as a result of this work and have asked him to integrate these ideas into their sentiment analysis system (contact: Senior Manager and Engineer at Amazon).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -