Integrating question classification and deep learning for improved answer selection
- Submitting institution
-
The University of Birmingham
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 53763177
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Proceedings of the 27th International Conference on Computational Linguistics
- First page
- 3283
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- August
- Year of publication
- 2018
- 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)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper describes work combining linguistic features with deep learning to produce state-of-the-art results in Answer Selection for Question Answering, an important application of NLP.
Our accuracy scores are listed on the Association of Computational Linguistics wiki page
(https://aclweb.org/aclwiki/Question_Answering_(State_of_the_art)) and were ranked best in
the world from the date of publication to April 2019 and are currently ranked second. The
current best system (Kamath 2019) builds on our work. We provide a web service to other researchers (to date accessed by 66 research/corporate groups to classify over 750,000 questions). COLING is ranked in the top two conferences for NLP.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -