Abstract
Natural Language Generation (NLG) systems generate texts in English and other human languages from non-linguistic input data. Usually there are a large number of possible texts that can communicate the input data, and NLG systems must choose one of these. We argue that style can be used by NLG systems to choose between possible texts, and explore how this can be done by (1) imitating a genre style, and (3) imitating an individual's style.
| Original language | English |
|---|---|
| Title of host publication | Style in Text: Creative Generation and Identification of Authorship |
| Subtitle of host publication | AISB 2008 Proceedings Volume 7 |
| Publisher | AISB |
| Pages | 26-33 |
| Number of pages | 8 |
| Volume | 7 |
| ISBN (Print) | 1 902956 66 4 |
| Publication status | Published - 2008 |
| Event | AISB'08 Symposium Style in Text: Creative Generation and Identification of Authorship - University of Aberdeen, Aberdeen, United Kingdom Duration: 3 Apr 2008 → 3 Apr 2008 http://www.aisb.org.uk/convention/aisb08/index.html |
Conference
| Conference | AISB'08 Symposium Style in Text |
|---|---|
| Country/Territory | United Kingdom |
| City | Aberdeen |
| Period | 3/04/08 → 3/04/08 |
| Internet address |
Bibliographical note
We would like to thank our colleagues in Aberdeen and Milton Keynes, the anonymous reviewers, and the tutors we worked with in skillsum for their insightful comments and suggestions. This work was funded by PACCIT-LINK grant ESRC RES-328-25-0026.Fingerprint
Dive into the research topics of 'Three Approaches to Generating Texts in Different Styles'. Together they form a unique fingerprint.Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS