This will require progress in cross language retrieval and machine translation.
Analogy-based machine translation, in particular the matching of source and target languages, is used as an example throughout the book.
The basic analogical machine translation architecture, involving matching, recombination and generation is also presented.
There has been related work in developing phrase-based models for statistical machine translation.
For machine translation the languages will determine which senses are relevant.
We also conducted some simple machine translation experiments using the word alignments thus obtained.
Nevertheless, machine translation can be quite impressive in the right circumstances.
Conventional machine translation systems designed for written language generally perform poorly when applied to spoken language.