Title | ||
---|---|---|
Concept Discovery for Language Understanding in an Information-query Dialogue System. |
Abstract | ||
---|---|---|
Most recent efficient statistical approaches for natural language understanding require a segmental annotation of training data. Such an annotation implies both to determine the concepts in a sentence and to link them to their corresponding word segments. In this paper we propose a two-steps alternative to the fully manual annotation of data: an initial unsupervised concept discovery, based on latent Dirichlet allocation, is followed by an automatic segmentation using integer linear optimisation. The relation between discovered topics and task-dependent concepts is evaluated on a spoken dialogue task for which a reference annotation is available. Topics and concepts are shown close enough to achieve a potential reduction of one half of the manual annotation cost. |
Year | Venue | Keywords |
---|---|---|
2011 | KDIR 2011: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND INFORMATION RETRIEVAL | Concept discovery,Language understanding,Latent Dirichlet analysis,Dialogue systems |
Field | DocType | Citations |
Integer,Training set,Latent Dirichlet allocation,Annotation,Computer science,Segmentation,Natural language understanding,Natural language processing,Artificial intelligence,Sentence,Language understanding | Conference | 1 |
PageRank | References | Authors |
0.36 | 4 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nathalie Camelin | 1 | 39 | 14.29 |
Boris Detienne | 2 | 53 | 5.78 |
Stéphane Huet | 3 | 40 | 9.15 |
Dominique Quadri | 4 | 35 | 6.18 |
F. Lefèvre | 5 | 77 | 8.35 |