Predicting the Compositionality of Nominal Compounds: Giving Word Embeddings a Hard Time
- Submitting institution
-
The University of Sheffield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 5217
- Type
- E - Conference contribution
- DOI
-
10.18653/v1/p16-1187
- Title of conference / published proceedings
- Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- First page
- 1986
- Volume
- 1: Long papers
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- August
- Year of publication
- 2016
- 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
-
3
- Research group(s)
-
D - Natural Language Processing
- Citation count
- 12
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is the first to provide a rigorous investigation of traditional and neural network methods for automatic compositionality detection, providing a new benchmark for the task. This is a challenging and timely topic, funded by Samsung Electronica Da Amazonia Ltda and relevant for academic and commercial research for applications involving machine translation, leading to talks including at Amazon (US) and Unbabel (Portugal). This paper appeared in the A* CORE Ranked conference ACL (acceptance rate 23%), and has been cited by groups like the Allen Institute for AI (doi.org/10.1162/tacl_a_00277) and in patent by the Educational Testing Service (USA-US10585985B1-https://patents.google.com/patent/US10585985B1/en).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -