CAM: A Combined Attention Model for Natural Language Inference
- Submitting institution
-
University of Sunderland
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 967
- Type
- E - Conference contribution
- DOI
-
10.1109/BigData.2018.8622057
- Title of conference / published proceedings
- Proceedings 2018 IEEE International Conference on Big Data
- First page
- 1009
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- December
- Year of publication
- 2018
- URL
-
http://sure.sunderland.ac.uk/id/eprint/10478/
- 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)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Natural language text often contains ambiguous words that can only be understood accurately by using contextual information. We explore the use of two variations of attention mechanisms as advanced neural network methods and empirically prove their different contribution to NLI tasks. This study has led to the development of a novel model by the co-authors, which exceeded the performance of some of state-of-arts models, as in Gajbhiye et al. 2020 https://doi.org/10.1007/978-3-030-61609-0_50. This research can contribute to many natural language tasks. For example, our methodology has been adopted for argument generation by Al-Khawaldeh et al. 2020 DOI:16.10089.JASC.2020.V7I3.453459.150801092
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -