e-SNLI: Natural Language Inference with Natural Language Explanations
- Submitting institution
-
University College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 14564
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018
- First page
- 9539
- Volume
- 2018-December
- Issue
- -
- ISSN
- 1049-5258
- Open access status
- Compliant
- Month of publication
- December
- 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
-
3
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Paradigm shift from training models based on individual training examples towards learning from rich natural language explanations. This resulted in models that can utilize these explanations to learn better sentence representations that improved the state-of-the-art on various downstream tasks. This approach is now being used by other researchers to develop deep learning models that can explain their predictions (see Thorne et al. “Generating Token-Level Explanations for Natural Language Inference.” NAACL 2019). Led to various invited talks (e.g. invited speaker at Alan Turing Institute workshop, EMNLP 2018 workshop, Imperial College London, University of Cambridge, University of Edinburgh).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -