ECAI 2004 Conference Paper

[full paper]

Finite-state models for computer assisted translation

Elsa Cubel, Jorge Civera, Juan M. Vilar, Antonio L. Lagarda, Francisco Casacuberta, Enrique Vidal, David Picó, Jorge González, Luis Rodríguez

Current methodologies for automatic translation cannot be expected to produce high quality translations. However, some techniques based on these methodologies can increase the productivity of human translators. The basis of one of these methodologies are finite-state transducers, which are adequate models for computer assisted translation. These models have proved to be very efficient in many pattern recognition and artificial intelligence tasks such as speech recognition, handwriting recognition and machine translation for specific tasks. These finite-state models present some advantages. On one hand, finite-state models can be learnt from bilingual corpus to infer transducers. On the other hand, there are well-known and efficient algorithms to perform the parse of the best translation according to these models (Viterbi search). In this paper, the concept of interactive search will be introduced along with some efficient techniques that solve the problem of producing a translation given a sentence to be translated and a prefix typed by the user. Needless to say that this system must run under real-time constraints to be useful for human translators. This approach have been tested on a corpus of printer manuals and the first results reflect that human translators would only need to type 25% of the characters, instead of the complete translated text, increasing in this way their throughput and reducing their effort.

Keywords: automatic translation, computer assisted translation, finite-state models, interactive search

Citation: Elsa Cubel, Jorge Civera, Juan M. Vilar, Antonio L. Lagarda, Francisco Casacuberta, Enrique Vidal, David Picó, Jorge González, Luis Rodríguez: Finite-state models for computer assisted translation. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.586-590.