Summary of the paper
| Title | Extracting Surface Realisation Templates from Corpora |
|---|---|
| Authors | Thiago D. Tadeu, Eder M. de Novais and Ivandré Paraboni |
| Abstract | In Natural Language Generation (NLG), template-based surface realisation is aneffective solution to the problem of producing surface strings from a givensemantic representation, but many applications may not be able to provide theinput knowledge in the required level of detail, which in turn may limit theuse of the available NLG resources. However, if we know in advance what themost likely output sentences are (e.g., because a corpus on the relevantapplication domain happens to be available), then corpus knowledge may be usedto quickly deploy a surface realisation engine for small-scale applications,for which it may be sufficient to select a sentence (in natural language) thatresembles the desired output, and then modify some or all of its constituentsaccordingly. In other words, the application may simply 'point to' an existingsentence in the corpus and specify only the changes that need to take place toobtain the desired surface string. In this paper we describe one such approachto surface realisation, in which we extract syntactically-structured templatesfrom a target corpus, and use these templates to produce existing and modifiedversions of the target sentences by a combination of canned text and basicdependency-tree operations. |
| Language | Other |
| Topics | Natural Language Generation, Tools, systems, applications, Other |
Full paper  |
Extracting Surface Realisation Templates from Corpora |
| Bibtex | @InProceedings{TADEU10.715, author = {Thiago D. Tadeu, Eder M. de Novais and Ivandré Paraboni}, title = {Extracting Surface Realisation Templates from Corpora}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |