Aligning packed dependency trees: a theory of composition for distributional semantics
- Submitting institution
-
University of Sussex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2860_61020
- Type
- D - Journal article
- DOI
-
10.1162/COLI_a_00265
- Title of journal
- Computational Linguistics
- Article number
- -
- First page
- 727
- Volume
- 42
- Issue
- 4
- ISSN
- 0891-2017
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2016
- URL
-
http://dx.doi.org/10.1162/COLI_a_00265
- 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
- Yes
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- "Published in Computational Linguistics, the leading international journal in Natural Language Processing with 2018 Google Scholar h5-index of 32. The paper presents a highly original approach to a central problem of NLP: how to compose the meaning of individual words to create a representation of the meaning of phrases and sentences. We provide a rigorous mathematical formulation, and performed a thorough experimental evaluation. It has achieved international impact, having been cited in Computational Linguistics [1], ACL [2], CONLL [3] and Journal of Language Modelling [4]. Field-weighted citation impact 1.5 (Scopus).
https://doi.org/10.1162/coli_a_00353
https://doi.org/10.18653/v1/P19-1571
https://doi.org/10.18653/v1/K18-1049
https://jlm.ipipan.waw.pl/index.php/JLM/article/view/201"
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -