Inproceedings,

Using WordNet-based context vectors to estimate the semantic relatedness of concepts

, and .
Proceedings of the EACL 2006 Workshop Making Sense of Sense-Bringing Computational Linguistics and Psycholinguistics Together, 1501, page 1--8. (2006)

Meta data

Tags

Users

  • @thoni

Comments and Reviewsshow / hide

  • @thoni
    11 years ago
    basically only incorporates a second-order-coocc of vectors built by WordNet glosses. Evaluation is pretty weak, to the point where some numbers aren't even explained. Evaluation was carried out on M&C dataset (30 pairs), which is REALLY weak.
Please log in to take part in the discussion (add own reviews or comments).