Proceedings chapter
Open access

Almost Flat Functional Semantics for Speech Translation

Presented at Manchester (UK), 18-22
Publication date2008

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.

Citation (ISO format)
RAYNER, Emmanuel et al. Almost Flat Functional Semantics for Speech Translation. In: Proceedings of the 22nd International Conference on Computational Linguistics (Coling). Manchester (UK). [s.l.] : [s.n.], 2008. p. 713–720.
Main files (1)
Proceedings chapter
  • PID : unige:3472

Technical informations

Creation10/02/2009 9:29:03 AM
First validation10/02/2009 9:29:03 AM
Update time03/14/2023 3:14:56 PM
Status update03/14/2023 3:14:56 PM
Last indexation02/12/2024 6:13:37 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack