Towards OpenLogos Hybrid Machine Translation

From HLT@INESC-ID

Revision as of 15:07, 20 March 2013 by Rdmr (talk | contribs) (Created page with "__NOTOC__ {{infobox|name=Anabela Barreiro |username=abarreiro |contact=abarreiro |phone=+351-213-100-313 |fax=+351-213-145-843 }} == Date == * 15:00, Friday, April 5<sup>th</su...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Anabela Barreiro
Anabela Barreiro

Date

  • 15:00, Friday, April 5th, 2013
  • Room 020

Speaker

Abstract

In this presentation, I will describe the OpenLogos machine translation system, its architecture and its semantico-syntactic representation language (SAL), which is the heart of the system. I will show how OpenLogos has addressed classic problems of rule-based machine translation, such as those related to ambiguity and complexity of natural language. I will exemplify the kind of quality translation that OpenLogos is capable of and show how OpenLogos has an ideal platform for a hybrid machine translation solution.

Bio

I am currently working on a post-doctoral research to build a new hybrid machine translation system that applies linguistically enhanced natural language processing resources, including semantico-syntactic knowledge, to statistical machine translation. From 1994 to 2001, I worked for Logos Corporation, a machine translation company located in New Jersey, in the USA. Logos Corporation was one of the longest running commercial machine translation companies in the world. I was the linguist responsible for the development of the English-Portuguese language pair of the Logos system. I also worked on the English-Spanish and English-Italian language pairs and participated in linguistic quality assurance tasks. Since the OpenLogos system has been publicly available as open source software, I have been one of its most enthusiastic advocates. My involvement with the OpenLogos open source initiative follows from my belief that the OpenLogos system will form the basis of the rules based component of a new hybrid MT system and will help the natural language processing community make significant scientific advances by using OpenLogos open source components.