Abstract | ||
---|---|---|
We introduce a novel semantic representation formalism, Almost Flat Functional semantics (AFF), which is designed as an intelligent compromise between linguistically motivated predicate/argument semantics and ad hoc engineering solutions based on flat feature/value lists; the central idea is to tag each semantic element with the functional marking which most closely surrounds it. We argue that AFF is well-suited for medium-vocabulary speech translation applications, and describe simple and general algorithms for parsing, generating and performing transfer using AFF representations. The formalism has been fully implemented within a medium-vocabulary interlingua-based Open Source speech translation system which translates between English, French, Japanese and Arabic. |
Year | Venue | Keywords |
---|---|---|
2008 | COLING | open source speech translation,semantic element,flat feature,engineering solution,aff representation,argument semantics,central idea,novel semantic representation formalism,flat functional semantics,medium-vocabulary speech translation application,almost flat functional semantics,generic algorithm |
Field | DocType | Volume |
Arabic,Computer science,Interlingua,Functional semantics,Artificial intelligence,Natural language processing,Speech translation,Predicate (grammar),Parsing,Formalism (philosophy),Semantics | Conference | C08-1 |
Citations | PageRank | References |
2 | 0.43 | 5 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Manny Rayner | 1 | 508 | 89.27 |
Pierrette Bouillon | 2 | 214 | 41.22 |
Beth Ann Hockey | 3 | 212 | 36.35 |
Yukie Nakao | 4 | 47 | 8.86 |