This paper examines the relevance of differential language expertise in ordinary conversation between speakers of Japanese as a first and second language. Adopting a conversation analytic perspective, the study focuses on other-repair as one sequential environment in which the participants recurrently orient to their differential linguistic knowledge. Specifically, it will be shown that languag...

Our task, broadly stated, is the development of systems for the understanding of narrative messages in limited domains. Improving the current state-of-the-art for such systems will require a better understanding of how to capture and utilize domain information, and how to effectively combine the various sources of information (syntactic, semantic, and discourse) to create a robust language anal...

This paper describes an architecture for performing anaphora resolution in a flexible way. Systems which conform to these guidelines are wellencapsulated and portable, and can be used to compare anaphora resolution techniques for new language understanding applications. Our implementation of the architecture in a pronoun resolution testing platform demonstrates the flexibility of the approach.

From February to April CRL carried out investigations into the modification of our l~n~Hsh name recognition software developed for MUC-6 [1] to Chinese and Spanish. In addition a Japanese system, developed under Tipster Phase I [2], was modified to comply with the MET task. Finally learning methods developed for MUC-6 were adapted to handle Chinese. All systems performed with good levels of acc...

The final evaluation of the information extraction portion of phase one of the ARPA Tipster Text program was conducted in July, 1993. Participants in this evaluation included not only the Tipster-supported information extraction contractors but thirteen other sites as well. This evaluation was the topic of the Fifth Message Understanding Conference (MUC-5), which was held in August, 1993, and c...

As a d ia log progresses the objects and ac t ions that are most re levant to the conversat ion, and hence in the focus of a t t e n t i o n of the d ia log p a r t i c i p a n t s , change. This paper describes a representa t ion of focus for language understanding systems, emphasizing i t s use in understanding taskor ien ted d ia logs . The representat ion h i g h l i g h t s tha t par t of ...

This report describes a telephone speech corpus collected at the Oregon Graduate Institute's Center for Spoken Language Understanding. Over four thousand people called in response to public requests. They were prompted by a recorded voice to say and spell their rst and last names|with and without pauses, to say what city they grew up in and what city they were calling from, and to answer two ye...