SRI International FASTUS System MUC-6 Test Results and Analysis

Abstract

INTRODUCTIO NSRI International participated in the MUC-6 evaluation using the latest version of SRI's FASTUS system [1] . The FASTUS system was originally developed for participation in the MUC-4 evaluatio n [3] in 1992, and the performance of FASTUS in MUC-4 helped demonstrate the viability of finit e state technologies in constrained natural-language understanding tasks . The system has undergon e significant revision since MUC-4, and it is safe to say that the current system does not share a singl e line of code with the original . The fundamental ideas behind FASTUS, however, are retained i n the current system : an architecture consisting of cascaded finite state transducers, each providin g an additional level of analysis of the input, together with merging of the final results . This paper will describe the version of the FASTUS system employed in MUC-6 and highlight the innovations that distinguish it from previous versions described in the literature . SRI used the FASTUS system for each of the MUC-6 tasks : the named entity task, the templateentity task, the coreference task, and the scenario template task . Because a single system, with a single configuration, was used to run all the tasks, and because the first three tasks are in som e sense prerequisites to the fourth, we will focus our attention in this paper on the scenario templat e task . BASIC FASTUSThe SRI FASTUS system is based on a series of finite-state transducers that compute the transformation of text from sequences of characters to domain templates . This architecture has proven t o be very flexible, and has been applied with success to a number of different information extractio n tasks in widely varying domains . We have applied FASTUS to extraction of information about terrorist incidents [3], extraction of information about joint ventures [2], indexing of legal document s for hypertext, extracting extensive information from military texts (Warbreaker Message Handler) , extraction of information from spoken dialogues [4], and a number of other smaller systems an d pilot applications . We have applied FASTUS to Japanese texts [2, 4] as well as English .Each transducer (or "phase") in the series takes the output of the previous phase and map s it into structures that comprise the input to the next phase, or that contain the domain templat e

Corpus-Based Analysis of Parenthetical Reporting Clauses

“…Three kinds of proper names were evaluated: person names, location names and organization names. Two human annotators independently developed the key templates 5 . Disagreements between annotators were solved by joint decision.…”

“…Dictionaries of the general language, essentially to identify unknown words Grammar rules are then applied to combine these informations to tag the expressions that are identified with the most appropriate semantic tag. Alembic [4], Proteus [11], and TextPro [7] (a descendant of Fastus [6,5]) are examples of systems that use this approach. This paper will only analyse rule-based systems.…”

Two Applications of Information Extraction to Biological Science Journal Articles: Enzyme Interactions and Protein Structures

“…One of several dozen systems designed to take part in the MUC evaluations over the years, the LaSIE system more or less ts the description of a generic IE system 10 . LaSIE is neither as`deep' as some earlier IE systems that attempted full syntactic, semantic and discourse processing 11 nor as`shallow' as some recent systems that use nite state pattern matching techniques to map directly from source texts to target templates 12 .…”

Untitled

“…(Appelt et al, 1995;Weischedel, 1995). Unfortunately, straightforward rules, such as <proper-noun> + <corporate designator> ==> <corporation> are not nearly adequate for state-of-the-art performance, nor do they capture typical naming conventions.…”