Abstract
Surface realisations typically depend on their target style and audience. A challenge in estimating a stylistic realiser from data is that humans vary significantly in their subjective perceptions of linguistic forms and styles, leading to almost no correlation between ratings of the same utterance. We address this problem in two steps. First, we estimate a mapping function between the linguistic features of a corpus of utterances and their human style ratings. Users are partitioned into clusters based on the similarity of their ratings, so that ratings for new utterances can be estimated, even for new, unknown users. In a second step, the estimated model is used to re-rank the outputs of a number of surface realisers to produce stylistically adaptive output. Results confirm that the generated styles are recognisable to human judges and that predictive models based on clusters of users lead to better rating predictions than models based on an average population of users.
Original language | English |
---|---|
Title of host publication | Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics |
Publisher | Association for Computational Linguistics |
Pages | 702-711 |
Number of pages | 10 |
ISBN (Print) | 9781937284787 |
DOIs | |
Publication status | Published - Apr 2014 |
Event | 14th Conference of the European Chapter of the Association for Computational Linguistics 2014 - Gothenburg, United Kingdom Duration: 26 Apr 2014 → 30 Apr 2014 |
Conference
Conference | 14th Conference of the European Chapter of the Association for Computational Linguistics 2014 |
---|---|
Abbreviated title | EACL 2014 |
Country/Territory | United Kingdom |
City | Gothenburg |
Period | 26/04/14 → 30/04/14 |
ASJC Scopus subject areas
- Software