The Message Understanding Conferences (MUCs) are gatherings of researchers in computational linguistics. All participants in the conference develop software systems which perform natural language understanding tasks defined by the conference committee. The systems are evaluated based on how their output compares with the output of human linguists. The MUC scoring software is used in that compar...

The TIPSTER Program began in June 1989 just after the conclusion of the second Message Understanding Conference (MUC-2). The concept which the Advanced Research Projects Agency (ARPA) put forward at that time was based on the promising results of that conference and on the belief that the technologies being demonstrated at MUC for the automated handling oflarge volumes of text would be of great...

This paper defines a methodology for automatically analyzing textual reports of events and synthesizing event data elements from the reports for automated input to a data base. The long-term goal of the work described is to develop a support technology for spec i f i c analytical functions related to the evaluation of daily message t ra f f ic in a mi l i tary environment. The approach taken le...

In this paper, we describe a novel spoken language understanding approach using two successive learners. The first learner is used to identify the topic of an input utterance. With the restriction of the recognized target topic, the second learner is trained to extract the corresponding slot-value pairs. The advantage of the proposed approach is that it is mainly datadriven and requires only mi...

LOLITA has been designed in such a way that the code implementing the MUC tasks is only a small part of the whole system. A core system provides complex facilities with the MUC system being built so that it utilises these facilities. Hence, after some background to the LOLITA project, the ‘core’ of LOLITA is described. This system description is substantially similar to that given for MUC-6 [1]...

The Fifth Message Understanding Conference (MUC-5) focused on the task of data extraction for tw o distinctly different applications, one within the domain of joint ventures (JV) and the other within the domain o f microelectronics (ME) . For each application, the task could be performed in either English and/or Japanese, giving four combinations : English Joint Ventures, Japanese Joint Venture...