Point at the triple: generation of text summaries from knowledge base triples
- Submitting institution
-
University of Southampton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 68650964
- Type
- D - Journal article
- DOI
-
10.1613/jair.1.11694
- Title of journal
- Journal of Artificial Intelligence Research
- Article number
- -
- First page
- 1
- Volume
- 69
- Issue
- -
- ISSN
- 1076-9757
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2020
- 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
- Humans find it hard to interpret raw data, so there is a clear need to automatically transform from data to something humans will understand. This paper (and accompanying IJCAI paper - https://bit.ly/3gw4Odl) is just an exemplary part of a larger body of our research studying how to build machines to transform data to human understandable, natural language. The paper builds upon work published in top venues including J. Web Semant. (http://dx.doi.org/10.1016/j.websem.2018.07.002), NAACL (https://bit.ly/3bF9JpE), COLING (https://bit.ly/2SDurgF), ESWC (https://doi.org/10.1007/978-3-319-93417-4_21) and LREC (https://bit.ly/2uuvV5b). The paper we authored about the dataset creation for this work was best paper at the 2018 CrowdBias workshop (https://bit.ly/2UI9JPp).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -