MT for Minority Languages Using Elicitation-Based Learning of Syntactic Transfer Rules
journal contributionposted on 01.01.1967 by Katharina Probst, Lorraine Levin, Erik Peterson, Alon Lavie, Jaime G. Carbonell
Any type of content formally published in an academic journal, usually following a peer-review process.
The AVENUE project contains a run-time machine translation program that is surrounded by pre- and post-run-time modules. The post-run-time module selects among translation alternatives. The pre-run-time modules are concerned with elicitation of data and automatic learning of transfer rules in order to facilitate the development of machine translation between a language with extensive resources for natural language processing and a language with few resources for natural language processing. This paper describes the run-time transfer-based machine translation system as well as two of the pre-run-time modules: elicitation of data from the minority language and automated learning of transfer rules from the elicited data.