Evaluating Composition Models for Verb Phrase Elliptical Sentence Embeddings.
- Submitting institution
-
University College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 16247
- Type
- E - Conference contribution
- DOI
-
10.18653/v1/N19-1023
- Title of conference / published proceedings
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1
- First page
- 261
- Volume
- 1
- Issue
- -
- ISSN
- 0000-0000
- Open access status
- Out of scope for open access requirements
- Month of publication
- June
- 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
-
1
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first paper that for the first time exceeded sentence boundaries and introduced a compositional discourse representation for models that unify logic and statistics in Natural Language Processing. It showed that traditional discourse resolution methods lead to semantic representations that can be implemented on natural language data, developed two large datasets with human annotations on disambiguation and paraphrasing tasks, showed that adding coreference improves the performance in general, and that compositional models provide better performances.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -