A hybrid approach to automatic derivation of class-based selectional preferences is proposed. A lexicon of selectional preferences can assist in handling several forms of ambiguity, a major problem for MT. The approach combines knowledge-rich parsing and lexicons, with statistics and corpus data. We illustrate the use of a selectional preference lexicon for anaphora resolution.

Machine Translation (MT) systems that process unrestricted text should be able to deal with words that are not found in the MT lexicon. Without some kind of recognition, the parse may be incomplete, there is no transfer for the unfound word, and tests for transfers for surrounding words will often fail, resulting in poor translation. Interestingly, not much has been published on unfound- word guessing in the context of MT although such work has been going on for other applications. In our work on the IBM MT system, we implemented a far-reaching strategy for recognizing unfound words based on rules of word formation and for generating transfers. What distinguishes our approach from others is the use of semantic and syntactic features for both analysis and transfer, a scoring system to assign levels of confidence to possible word structures, and the creation of transfers in the transformation component. We also successfully applied rules of derivational morphological analysis to non-derived unfound words.

Translations produced by an MT system can automatically be assigned a number that reflects the MT system’s confidence in their quality. We describe the design of such a confidence index, with focus on the contribution of source analysis, which plays a crucial role in many MT systems, including ours. Various problematic areas of source analysis are identified, and their impact on the overall confidence index is given. We will describe two methods of training the confidence index, one by hand-tuning of the heuristics, the other by linear regression analysis.

We present a newly designed transformational system for the MT system LMT, consisting of a transformational formalism, LMT-TL, and an algorithm for applying transformations written in this formalism. LMT-TL is both expressive and simple because of the systematic use of a powerful pattern matching mechanism that focuses on dependency trees. LMT-TL is a language in its own right, with no “escapes” to underlying programming languages. We first provide an overview of the complete LMT translation process (all newly redesigned), and then give a self-contained description of LMT-TL, with examples.

IBM is engaged in advanced research and development projects on various aspects of machine translation, between several language pairs. The activities reported on hero are all parts of a rather large-scale, international effort, following Michael McCord’s LMT approach. The paper focuses on seven selected topics: recent enhancements made in the Slot Grammar formalism and the specific analysis components; specification of a semantic type hierarchy and its use for verb sense disambiguation; incorporation of statistical techniques in the translation process; anaphora resolution; linkage of target morphology modules; methods for the construction of large MT lexicons; and interactive disambiguation.