How semantic is Latent Semantic Analysis?

Tonio Wandmacher


Abstract
In the past decade, Latent Semantic Analysis (LSA) was used in many NLP approaches with sometimes remarkable success. However, its abilities to express semantic relatedness were not yet systematically investigated. This is the aim of our work, where LSA is applied to a general text corpus (German newspaper), and for a test vocabulary, the lexical relations between a test word and its closest neighbours are analysed. These results are compared to the results from a collocation analysis.
Anthology ID:
2005.jeptalnrecital-recital.1
Volume:
Actes de la 12ème conférence sur le Traitement Automatique des Langues Naturelles. REncontres jeunes Chercheurs en Informatique pour le Traitement Automatique des Langues
Month:
June
Year:
2005
Address:
Dourdan, France
Editors:
Nicolas Hernandez, Guillaume Pitel
Venue:
JEP/TALN/RECITAL
SIG:
Publisher:
ATALA
Note:
Pages:
525–534
Language:
URL:
https://aclanthology.org/2005.jeptalnrecital-recital.1
DOI:
Bibkey:
Cite (ACL):
Tonio Wandmacher. 2005. How semantic is Latent Semantic Analysis?. In Actes de la 12ème conférence sur le Traitement Automatique des Langues Naturelles. REncontres jeunes Chercheurs en Informatique pour le Traitement Automatique des Langues, pages 525–534, Dourdan, France. ATALA.
Cite (Informal):
How semantic is Latent Semantic Analysis? (Wandmacher, JEP/TALN/RECITAL 2005)
Copy Citation:
PDF:
https://aclanthology.org/2005.jeptalnrecital-recital.1.pdf