This paper describes our research into generating Dutch noun phrases as descriptions of furniture objects or people. This is usually done in two steps: attribute selection and realisation. This research focuses only on the realisation step: generating a noun phrase from given attributes. The research is done on the Dutch version of the TUNA-corpus, which contains annotated human-produced descriptions. Three algorithms were developed for this task, each an improvement over the last. We extracted the lexical choice from the D-TUNA corpus, and used templates generated from the corpus which specified the order of attributes. The algorithms were then evaluated for string similarity with the original human descriptions from the corpus, and a human evaluation was carried out which tested clarity and fluency. A steady improvement of scores in both the automatic and human evaluation was observed for each new version of the algorithm.
|Title of host publication||Proceedings of PRE-CogSci 2013 – Bridging the Gap between Cognitive and Computational Approaches to Reference|
|Editors||A. Gatt, R. van Gompel, E. Gurman-Bard, E. Krahmer, K. van Deemter|
|Place of Publication||Tilburg, The Netherlands|
|Number of pages||6|
|ISBN (Print)||not assigned|
|Publication status||Published - Jul 2013|
|Event||PRE-CogSci 2013 – Bridging the Gap between Cognitive and Computational Approaches to Reference - Berlin, Germany|
Duration: 31 Jul 2013 → 31 Jul 2013
|Workshop||PRE-CogSci 2013 – Bridging the Gap between Cognitive and Computational Approaches to Reference|
|Period||31/07/13 → 31/07/13|
Hoek, M., & Theune, M. (2013). Generation of Dutch referring expressions using the D-TUNA corpus. In A. Gatt, R. van Gompel, E. Gurman-Bard, E. Krahmer, & K. van Deemter (Eds.), Proceedings of PRE-CogSci 2013 – Bridging the Gap between Cognitive and Computational Approaches to Reference (pp. -). Tilburg, The Netherlands: Tilburg University.