Learning Finite-State Models For Language Understanding

Language Understanding in limited domains is here approached as a problem of language tra~lation in which the target language is a ]o~nal language rather than a natural one. Finite-state transducers are used to model the translation process. Furthermore, these models are automatically learned from ironing data consisting of pairs of natural-language/formal-language sentences. The need for training data is dramatically reduced by performing a two-step learning process based on !exical/phrase categorization. Successful experiments are presented on a task consisting in the ~anderstanding ~ of Spanish natural-language sentences describing dates and times, where the target formal language is the one used in the popular Unix command ~at". 1 I n t r o d u c t i o n Language Understanding (LU) has been the focus of much research work in the last twenty years. Many classical approaches typically consider LU from a linguistically motivated, generalistic point of view. Nevertheless, it is interesting to note tllat, in contrast with some general-purpose formulations of LU, many applications of interest to industry and business have limited domains; that is, lexicons are of small size and the semantic universe is limited. If we restrict ourselves to these kinds of tasks, many aspects of system design can be dramatically simplified. In fact, under the limited-domain framework, the ultimate goal Of a system is to driue the actions associated to the meaning conveyed by the sentences issued by the users. Since actions are to be performed by machines, the understanding problem can then be simply formulated as translating the natural language sentences into .?orma/sentences of an adequate (computer) command language in which the actions to be carried out can.be specified. For example, "understanding" natural language (spOken) queries to a database can be seen as "translating" these queries into appropriate computer-language code to access the database. Clearly, under such an assumption, LU can be seen as a possibly simpler case of Language Translation in which the output language is forma/rather than natural Hopefully, these simplifications can lead to new systems that are more compact and faster to build thant those developed under more traditional paradigms. This would entail i) to devise simple and easily understandable models for LU, ii) to formulate LU as some kind of optimal search through an adequate structure based on these models, and iii) to develop techniques to actually learn the LU models from training data of each considered task. All these requirements can be easily met through the use of Finite-State Translation Models. The capabilities of Finite-State Models (FSM) have been the object of much debate in the past few years. On the one hand, in the Natural Language (NL) community, FSMs have often * Work partially supported by the Spanish CICYT under grant TIC-0745-CO2