Statistical Language Understanding Using Frame Semantics

This is a very young project, operational for only a few months . The focus of the effort is dataextraction, the identification of instances of data-classes in "commercial" text -e .g., newspapers, technical reports, business correspondence, intelligence briefs . Instances of data-classes in text are phrases which identify factual content, such as names of people or organizations, products, fin...

Time-offset interaction is a new technology that enables conversational interaction with a person who is not present, using pre-recorded video statements. Statements were recorded by Pinchas Gutter, a Holocaust survivor, talking about his personal experiences before, during and after the Holocaust. Participants interacted with the statements through a “Wizard of Oz” system, where live operators...

In this paper we revisit the task of quantitative evaluation of coreference resolution systems. We review the most commonly used metrics (MUC, B, CEAF and BLANC) on the basis of their evaluation of coreference resolution in five texts from the OntoNotes corpus. We examine both the correlation between the metrics and the degree to which our human judgement of coreference resolution agrees with t...

The third thread is the sponsorship of the international Message Understanding Conferences (MUC's) and Text Retrieval Conferences (TREC's). These conferences, which evaluated the state of the art and promoted text-processing R&D outside of the TIPSTER Text contracts, were organized by NRaD and NIST. MUC-1 and MUC-2 preceded and set the stage for TIPSTER, before the sponsorship of these conferen...

We describe a language understanding model in which idioms, like other units of linguistic knowledge, are treated as constructions linking elements of form with elements of meaning. They may also, however, invoke additional metaphorical mappings that can actively constrain both the interpretation and acceptability of idiomatic expressions. A wide variety of idiomatic phenomena, including compos...

This paper deals with commonsense understanding of part-whole relations. A unifying definition for the different kinds of parts is proposed for one domain, that of rigid, man-made objects. First, the representation of objects via basic dimensions, reference systems and attributes is described. Then, different kinds of parts, based on the classification of Gerstl and Pribbenow (1996), are examin...