No abstract

No abstract

Textual question answering is a technique of extracting a sentence or text snippet from a document or document collection that responds directly to a query. Open-domain textual question answering presupposes that questions are natural and unrestricted with respect to topic. The question answering (Q/A) techniques, as embodied in today's systems, can be roughly divided into two types: (1) techniques for Information Seeking (IS), which localize the answer in vast document collections; and (2) techniques for Reading Comprehension (RC) that answer a series of questions related to a given document. Although these two types of techniques and systems are different, it is desirable to combine them for enabling more advanced forms of Q/A. This paper discusses an approach that successfully enhanced an existing IS system with RC capabilities. This enhancement is important because advanced Q/A, as exemplified by the ARDA AQUAINT program, is moving towards Q/A systems that incorporate semantic and pragmatic knowledge enabling dialogue-based Q/A. Because today's RC systems involve a short series of questions in context, they represent a rudimentary form of interactive Q/A which constitutes a possible foundation for more advanced forms of dialogue-based Q/A.

In this paper we present a new, multilingual data-driven method for coreference resolution as implemented in the SWIZZLE system. The results obtained after training this system on a bilingual corpus of English and Romanian tagged texts, outperformed coreference resolution in each of the individual languages.

Japanese was one of the languages selected for evaluation of named entity identification algorithms in the TIPSTER-sponsored Multilingual Entity Task (MET) program. As with the Spanish and Chinese groups (Table 1), Japanese systems automatically marked the names of organizations, people, and places within entity name expressions (ENAMEX), dates and times within time expressions (TIMEX), and percents and money within number expressions (NUMEX). The participant Japanese systems were developed in a fourmonth period of time and output results comparable to the Message Understanding Conference-6 (MUC-6) [1] English language systems with F-Measures between 70 -90% [21.