Abstract
Low-dimensional representations for lexical co-occurrence data have become increasingly important in alleviating the sparse data problem inherent in natural language processing tasks. This work presents a distributed latent variable model for inducing these low-dimensional representations. The model takes inspiration from both connectionist language models [1, 16] and latent variable models [13, 9]. We give results which show that the new model significantly improves both bigram and trigram models.
Original language | English |
---|---|
Title of host publication | AISTATS 2005 - Proceedings of the 10th International Workshop on Artificial Intelligence and Statistics |
Pages | 25-32 |
Number of pages | 8 |
State | Published - 2005 |
Externally published | Yes |
Event | 10th International Workshop on Artificial Intelligence and Statistics, AISTATS 2005 - Hastings, Christ Church, Barbados Duration: 6 Jan 2005 → 8 Jan 2005 |
Publication series
Name | AISTATS 2005 - Proceedings of the 10th International Workshop on Artificial Intelligence and Statistics |
---|
Conference
Conference | 10th International Workshop on Artificial Intelligence and Statistics, AISTATS 2005 |
---|---|
Country/Territory | Barbados |
City | Hastings, Christ Church |
Period | 6/01/05 → 8/01/05 |