Description: This paper discusses LASSO, a tool for surfing the answer net. Abstract: This paper presents the architecture, operation and results obtained with the LASSO system developed in the Natural Language Processing Laboratory at SMU. The system relies on a combination of syntactic and semantic techniques, and lightweight abductive inference to find answers. The search for the answer is based on a novel form of indexing called paragraph indexing. A score of 55.5% for short answers and 64.5% for long answers was achieved.

Description: This paper discusses an automatic method for generating sense tagged corpora. Abstract: The unavailability of very large corpora with semantically disambiguated words is a major limitation in text processing research. For example, statistical methods for word sense disambiguation of free text are known to achieve high accuracy results when large corpora are available to develop context rules, to train and test them. This article presents a novel approach to automatically generate arbitrarily large corpora for word senses. The method is based on (1) the information provided in WordNet, used to formulate queries consisting of synonyms or definitions of word senses, and (2) the information gathered from Internet using existing search engines. The method was tested on 120 word senses and a precision of 91% was observed.

Description: This paper discusses a WordNet-based interface to Internet search engines. A vast amount of information is available on the Internet, and naturally, many information gathering tools have been developed. Several search engines with different characteristics, such as Alta Vista, Lycos, Infoseek, and others are available. However, the web information retrieval technology is still in its infancy, and there is need for considerable improvement. Some inherent difficulties are: (1) the web information is diverse and highly unstructured, (2) the size of information is large and it grows at an exponential rate, and (3) the current search engine technology is still rudimentary. While the first two issues are more profound and require long term solutions, it may be possible to develop software around the search engines to improve the quality of the information retrieved. In this paper the authors present a natural language interface system to a search engine and discuss some of the results obtained.

Description: This paper discusses application of qualitative and quantitative content analysis techniques to assess metadata records from 42 Federal agencies' implementation of the Government Information Locator Service (GILS). GILS databases respond to a late-1994 initiative to "identify public information resources throughout the Federal government, describe the information available in those resources, and provide assistance in obtaining the information [and] serve as a tool to improve agency electronic records management practices". GILS metadata records describe agencies' automated information systems, Privacy Act systems of records, and locators that cover its information dissemination products. The authors used record content analysis, and several other methods, to examine whether GILS is meeting user expectations. Criteria used in the current analysis were informed in part by results of user and service-implementor questionnaires and focus groups. The record content analysis itself, in turn, informed creation of a scripted online assessment for users, and data from that user assessment supplemented results of the content analysis. The quality of metadata for networked resources is as of yet a relatively unexplored research area. At this point, no consensus has been reached on operational and conceptual definitions of quality; likewise, validated procedures for assessing metadata are lacking. On the basis of the ...