Genichiro Kikui

Learn More
In this paper we study the trigger-based language model, which can model dependencies between words longer than those modeled by the n-gram language model. Generally in language modeling, when the training corpus matches the target task, its size is typically small, and therefore insufficient for providing reliable probability estimates. On the other hand,(More)
In order to accomplish the deep semantic understanding of a language, it is essential to analyze the meaning of predicate phrases, a content word plus functional expressions. In agglutinating languages such as Japanese, however, sentential predicates are multi-morpheme expressions and all the functional expressions including those unnecessary to the meaning(More)
Assisting in foreign language learning is one of the major areas in which natural language processing technology can contribute. This paper proposes a computerized method of measuring communicative skill in English as a foreign language. The proposed method consists of two parts. The first part involves a test sentence selection part to achieve precise(More)
We suggest a naïve Bayes method for Japanese recipe pairing which uses ingredients of main and side dishes. For every pair of ingredients in the learning data, we calculate the probability of the co-occurrence. For a main dish of the evaluation, we guess a side dish whose posterior probability has the maximum value. In our experiment, the domain of(More)
This paper describes an IR (Information Retrieval) approach to identifying the ICD-10 code of a medical term, such as a disease name or a description of a symptom or a complaint), in a medical text. In this approach, we prepare a dictionary of disease names, each paired with a corresponding ICD-10 code(s). The system searches for the disease name most(More)
In this paper, we show a special example distribution on which the learner can guess a correct simple deterministic grammar in polynomial time from membership queries and random examples. At first, we show a learning algorithm of simple deterministic languages from membership and equivalence queries. This algorithm is not a polynomial time algorithm but,(More)
Much natural language processing still depends on the Euclidean (cosine) distance function between two feature vectors, but this has severe problems with regard to feature weightings and feature correlations. To answer these problems, we propose an optimal metric distance that can be used as an alternative to the cosine distance, thus accommodating the two(More)
  • 1