This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully. The model does not only select attributes and values for referring to a target referent, but also performs Linguistic Realisation, generating an actual Noun Phrase. Our evaluations suggest that the attribute selection aspect of the algorithm exceeds classic REG algorithms, while the Noun Phrases generated are as similar to those in a previously developed corpus as were Noun Phrases produced by a new set of human speakers.
|Title of host publication||Proceedings of the 11th International Conference on Natural Language Generation|
|Editors||Emiel Krahmer, Albert Gatt, Martijn Goudbeek|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||10|
|Publication status||Published - Nov 2018|
|Event||11th International Conference on Natural Language Generation (INLG 2018) - Tilburg University, Tilburg, Netherlands|
Duration: 5 Nov 2018 → 8 Nov 2018
|Conference||11th International Conference on Natural Language Generation (INLG 2018)|
|Period||5/11/18 → 8/11/18|
Li, X., Van Deemter, K. J., & Lin, C. (2018). Statistical NLG for Generating the Content and Form of Referring Expressions. In E. Krahmer, A. Gatt, & M. Goudbeek (Eds.), Proceedings of the 11th International Conference on Natural Language Generation (pp. 482-291). Association for Computational Linguistics (ACL).