Summary of the paper
| Title | Corpus-based Referring Expressions Generation |
|---|---|
| Authors | Hilder Pereira, Eder Novais, Andre Mariotti and Ivandre Paraboni |
| Abstract | In Natural Language Generation, the task of attribute selection (AS) consists of determining the appropriate attribute-value pairs (or semantic properties) that represent the contents of a referring expression. Existing work on AS includes a wide range of algorithmic solutions to the problem, but the recent availability of corpora annotated with referring expressions data suggests that corpus-based AS strategies become possible as well. In this work we tentatively discuss a number of AS strategies using both semantic and surface information obtained from a corpus of this kind. Relying on semantic information, we attempt to learn both global and individual AS strategies that could be applied to a standard AS algorithm in order to generate descriptions found in the corpus. As an alternative, and perhaps less traditional approach, we also use surface information to build statistical language models of the referring expressions that are most likely to occur in the corpus, and let the model probabilities guide attribute selection. |
| Topics | Natural Language Generation, Language modelling |
Full paper  |
Corpus-based Referring Expressions Generation |
| Bibtex | @InProceedings{PEREIRA12.152, author = {Hilder Pereira and Eder Novais and Andre Mariotti and Ivandre Paraboni}, title = {Corpus-based Referring Expressions Generation}, booktitle = {Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12)}, year = {2012}, month = {may}, date = {23-25}, address = {Istanbul, Turkey}, editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Mehmet Uğur Doğan and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis}, publisher = {European Language Resources Association (ELRA)}, isbn = {978-2-9517408-7-7}, language = {english} } |