This page describes ongoing work to incorporate more lexical semantics into DELPH-IN.
Prelimary work is being done using the ERG and wordnet, mainly at NTU (FrancisBond, MathieuMorey) and UW (ZinaPozen).
Content
- Some early discussions at the Suquamish Summit
- Some thoughts on mapping between ERG and Wordnet predicates
- MRS mini-modelling Sympoisum at UW
- Semcor Wordnet-ERG mapping and link to data download
- Discussions at the Saarland Summit
To Maybe Do
- learn first senses from a large corpus in the style of McCarthy et al (2004) and use these to train the generative model — especially useful for non-English
References
- Sanae Fujita, Francis Bond, Stephan Oepen, and Takaaki Tanaka (2007) Exploiting semantic information for HPSG parse selection. In ACL 2007 Workshop on Deep Linguistic Processing, pages 25–32, Prague. (.bib)
- Stephan Oepen, Erik Velldal, Jan Tore Lønning, Paul Meurer, Victoria Rosén, and Dan Flickinger. Towards hybrid quality-oriented machine translation. On linguistics and probabilities in MT. In Proceedings of the 10th International Conference on Theoretical and Methodological Issues in Machine Translation, Skövde, Sweden, 2007.
- E. Velldal. Empirical Realization Ranking Ph.D. thesis, Department of Informatics, University of Oslo Oslo, Norway, 2008
- Sanae Fujita, Francis Bond, Takaaki Tanaka and Stephan Oepen (2010). Exploiting Semantic Information for HPSG Parse Selection. Research on Language and Computation, 8(1), 1–22.
Last update: 2013-07-29 by FrancisBond [edit]