Virginia Teller

Learn More
We present an algorithm for segmenting unrestricted Japanese text that is able to detect up to 98% of the words in a corpus. The segmentation technique, which is simple and extremely fast, does not depend on a lexicon or any formal notion of what a word is in Japanese, and the training procedure does not require annotated text of any kind. Relying almost(More)
  • Janet Dean Fodor, William Gregory Sakas, Carrie Crowther, Atsu Inoue, Xuan-Nga Kam, Yukiko Koizumi +10 others
  • 2004
1. The research project * Our research group has built a research environment for testing models of syntactic parameter setting. We have created a domain of 3,072 languages with up to 1,432 sentences in each, defined by a set of Universal Grammar (UG) rules and 13 (so far) binary parameters. The languages resemble human languages in many respects, though(More)
The thesis presents a framework that can be used for empirical and formal analysis of parameter setting models of language acquisition. Such models attempt to mirror computationally the process by which children acquire the grammar of their native language. Research into formal language learning theory standardly focuses on issues of learnability – Under(More)
Syntactic parameter setting has proven extremely difficult to model. The original 'switch-setting' m etaphor failed because parametrically relevant properties of a natural language sentence cannot be recognize d withou t considerable structural analy sis. The result has been a move to trial-and-error learners which attempt to guess a grammar that can(More)
We report on a project to develop a stochastic lexical analyzer for Japanese and to compare the accuracy of this approach with the results obtained using conventional rule-based methods. In contrast with standard, knowledge intensive methods, the stochastic approach to lexical analysis uses statistical techniques that are based on probabil-istic models.(More)
Hunter College teaches introductory AI as a one semester, advanced undergraduate elective that focuses on issues in three areas: state-space search and control, knowledge representation, and Lisp. The search component defines AI methodology and conveys how the computing world views the field; knowledge representation illustrates how AI sees the real world;(More)
  • 1