Augmenting word2vec with latent Dirichlet allocation within a clinical application

Akshay Budhkar, Frank Rudzicz


Abstract
This paper presents three hybrid models that directly combine latent Dirichlet allocation and word embedding for distinguishing between speakers with and without Alzheimer’s disease from transcripts of picture descriptions. Two of our models get F-scores over the current state-of-the-art using automatic methods on the DementiaBank dataset.
Anthology ID:
N19-1414
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4095–4099
Language:
URL:
https://aclanthology.org/N19-1414
DOI:
10.18653/v1/N19-1414
Bibkey:
Cite (ACL):
Akshay Budhkar and Frank Rudzicz. 2019. Augmenting word2vec with latent Dirichlet allocation within a clinical application. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4095–4099, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Augmenting word2vec with latent Dirichlet allocation within a clinical application (Budhkar & Rudzicz, NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1414.pdf
Video:
 https://vimeo.com/359723663