Preference-based interactive multi-document summarisation
- Submitting institution
-
Royal Holloway and Bedford New College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 35930686
- Type
- D - Journal article
- DOI
-
10.1007/s10791-019-09367-8
- Title of journal
- Information Retrieval Journal
- Article number
- -
- First page
- 1
- Volume
- 23
- Issue
- -
- ISSN
- 1386-4564
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2019
- 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
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work proposes the first practical preference-based interactive document summarization system. OpenAI recently extends this work to build a summarization system (https://arxiv.org/pdf/1909.08593.pdf). Compared to existing summarization systems, the proposed method is data efficient and able to provide user-tailored summaries. This paper extends our earlier work published on EMNLP 2018 (acceptance rate 25.5%; a premier conference in natural language processing).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -