Yevgeny Ludovik

Learn More
This paper describes the systems used by CRL in the Cross-lingual IR and Q&A tracks. The cross-language experiment was unique in that it was run interactively with a mono-lingual user simulating how a true cross-language system might be used. The methods used in the Q&A system are based on language processing technology developed at CRL for machine(More)
We have developed a method for answering single answer questions automatically using a collection of documents or the Internet as a source of data for the production of the answer. Examples of such questions are ‘What is the melting point of tin?’, and ‘Who wrote the novel Moby Dick?’. The approach we have adopted to the problem uses the Mikrokosmos(More)
Work on the production of texts in English describing instances of a particular event type from multiple news sources will be described. A system has been developed which extracts events , such as meetings, from texts in English, Russian, Spanish, and Japanese. The extraction is currently carried out using only ontological information. The results of a set(More)
Our principle objective was to reduce the error rate of speech recognition systems used by professional translators. Our work concentrated on Spanish-to-English translation. In a baseline study we estimated the error rate of an off-the-shelf recognizer to be 9.98%. In this paper we describe two independent methods of improving speech recognizers: a machine(More)
In this paper we describe a lexical disambiguation algorithm based on a statistical language model we call maximum likelihood disambiguation. The maximum likelihood method depends solely on the target language. The model was trained on a corpus of American English newspaper texts. Its performance was tested using output from a transfer based translation(More)
  • 1