ITP: description of the Interpretext system as used for MUC-3
نویسندگان
چکیده
The Message Handler identifies an individual MUC message unit and controls the flow o f operations of the whole system for one message . It reads sentences, and sends one sentence at a time to the ITP Natural Language Understanding Module . It prunes temporal and locative expressions, which are added back later to modify events . The ITP NLU Module parses one sentence, and maps its parse tree onto a Discourse Representation Structure (DRS) [8],[1] . This DRS is added to the DRS for the whole segment . Temporal/locative reasoning, anaphora resolutio n and discourse segmentation operate upon this larger DRS. When reading sentences for one message is completed, the Message Handler receives the resulting analysis from the ITP NL U Module . The resulting Cognitive Model is a segmented discourse structure for the whole message . The Message Handler sends one discourse segment at a time to the MUC3 Template Reasonin g Module . It fills all of the possible templates based on the information in the segment . MUC3 Message Handler MUC 3 TST Text MUC 3 Template Reasoning Module
منابع مشابه
ITP Interpretext system: MUC-3 test results and analysis
ITP's results are shown in Figure 1 . The ITP system was second highest in precision (46%) when all templates were considered, and at the same time achieved a credible recall percentage (20%) . Our overgeneration rate was second best (34%) . ITP was a very close second in both precisio n and overgeneration, as the top percentages were 48 and 33 to ITP's 46 and 34 . The major limitin g factor in...
متن کاملUniversity of Durham: Description of the LOLITA system as Used in MUC-7
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]...
متن کاملUniversity of Maryland/ConQuest: description of the ICTOAN system as used for MUC-4
The ICTOAN system is a natural language processing system developed jointly by ConQuest, Inc . and the University of Maryland Baltimore County. The system was written from scratch during the first five months of 1992 using an estimated eight person-months of labor . The template generation routines were reused from our MUC-3 system [1], providing leverage of perhaps one person-month . Adaptatio...
متن کاملUnisys: description of the Unisys system used for MUC-3
This paper describes the Unisys MUC-3 text understanding system, a system based upon a three tiered approach to text processing in which a powerful knowledge-based form of information retrieval plays a central role . This knowledge-based form of information retrieval makes it possible to define a n effective level of text analysis that falls somewhere between what is possible with standard keyw...
متن کامل