Abstract | ||
---|---|---|
Recent years' most efficient approaches for language understanding are statistical. These approaches benefit from a segmental semantic annotation of corpora. To reduce the production cost of such corpora, this paper proposes a method that is able to match first identified concepts with word sequences in an unsupervised way. This method based on automatic alignment is used by an understanding system based on conditional random fields and is evaluated on a spoken dialogue task using either manual or automatic transcripts. |
Year | Venue | Keywords |
---|---|---|
2011 | ULNLP@EMNLP | efficient approach,conditional random field,unsupervised alignment,dialogue task,understanding system,language understanding,automatic transcript,recent year,production cost,automatic alignment,segmental-based language understanding,segmental semantic annotation |
Field | DocType | Volume |
Conditional random field,Semantic annotation,Computer science,Production cost,Speech recognition,Artificial intelligence,Natural language processing,Language understanding | Conference | W11-22 |
Citations | PageRank | References |
4 | 0.40 | 14 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stéphane Huet | 1 | 40 | 9.15 |
Fabrice Lefèvre | 2 | 185 | 26.62 |