We propose a knowledge-based approach relying on the rich semantic information of BabelNet, for obtaining continuous representations for individual word senses
and by leveraging these representations and lexical-semantic knowledge, we put forward a semantic similarity measure with state-of-the-art performance on multiple datasets

Downloads

SensEmbed vectors: Sense embeddings


SensEmbed vectors: Synset embeddings 


SensEmbed+ vectors: Word, Sense and Synset embeddings trained on September 2014 English Wikipedia

SensEmbed+ vectors: Word, Sense and Synset embeddings trained on May 2018 English Wikipedia

 
 

Ignacio Iacobacci, Mohammad Taher Pilehvar and Roberto Navigli, SensEmbed: Learning Sense Embeddings for Word and Relational Similarity. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (ACL-IJCNLP 2015), Beijing, China, July 26-31, 2015.

Contact

Ignacio Iacobacci
Mohammad Taher Pilehvar

iacobacci [at] di.uniroma1 [dot] it

mp792 [at] cam [dot] ac [dot] uk

Roberto Navigli

navigli [at] di.uniroma1 [dot] it

 


SensEmbed: Learning Sense Embeddings for Word and Relational Similarityis licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 License.

This site was designed with the
.com
website builder. Create your website today.
Start Now