Sense Alignment of Wiktionary and OmegaWiki

Similarity-based Alignment

Michael Matuschek and Christian M. Meyer and Iryna Gurevych:
Multilingual Knowledge in Aligned Wiktionary and OmegaWiki for Translation Applications, in: Translation: Computation, Corpora, Cognition (TC3) 3(1): Special Issue “Language Technology for a Multilingual Europe”, 87–118.

Resource Download

Please have a look at the readme file for further explanations of these files.

Joint Alignment

Michael Matuschek and Iryna Gurevych:
High Performance Word Sense Alignment by Joint Modeling of Sense Distance and Gloss Similarity, in: Proceedings of the the 25th International Conference on Computational Linguistics (COLING 2014), pp. 245-256, August 2014, Dublin, Ireland.

Michael Matuschek:
Word Sense Alignment of Lexical Resources. PhD Thesis, Technische Universität Darmstadt, September 2014.

Resource Download

  • Full alignment of Wiktionary and OmegaWiki (v2.0, 2014-10-14, .csv, 439 KB)
    This alignment was created based on the same gold standard as above, but using a Machine Learning approach combining Dijkstra-WSA distances and gloss similarities.