Description of the UMass system as used for MUC-6

Abstract

Information extraction research at the University of Massachusetts is based on portable, trainable languag e processing components . Some components are more effective than others, some have been under developmen t longer than others, but in all cases, we are working to eliminate manual knowledge engineering . Although UMas s has participated in previous MUC evaluations, all of our information extraction software has been redesigned an d rewritten since MUC-5, so we are evaluating a completely new system this year .In particular, we are working with new string recognition specialists (for Named Entities), a new part-of-speech tagger, a new sentence analyzer, a new and fully automated dictionary construction algorithm, a new discours e analyzer, and a new coreference analyzer . The most interesting components in our system are CRYSTAL (whic h generates a concept node dictionary) [13], WRAP-UP (which establishes relational links between entities) [14, 15 , 16], and RESOLVE (the coreference analyzer) [8] . Each of these components utilizes machine learning techniques i n order to customize crucial extraction capabilities based on representative training texts .Our preparations for MUC-6 began on June 19 (at the release of the Call for Participation) and ended on Octobe r 2 when we began our test runs . All of our ST-specific training began in September with the release of the ST keys . As much as we try to exploit trainable technologies, there are nevertheless places where some amount of manua l coding is still needed . For example, we needed to write string manipulation functions to trim output strings in a n effort to generate slot fills consistent with the MUC-6 slot fill guidelines . We also needed to create template parser s and text marking interfaces in order to map the MUC-6 training documents into data usable by our trainabl e components.

A Context-Restricted Multi-Stage Korean Coreference Resolution Model

“…The operating system was Windows 7, and Python 2.7 was used as the programming language. To evaluate the system, we used MUC method as an evaluation measure which has been used during recent many years for coreference resolution [3]. MUC method evaluates the system based on links existing among mentions.…”

An information extraction approach to reorganizing and summarizing specifications

“…The SRI system FASTUS [24], the UMass system [15], and the NYU systems [20,21,57] among others made extensive use of patterns in recognizing various tokens and concepts. MUC-7 [33] tasks included development of potentially reusable domain-independent information extraction modules for marking named entities, dates, times, money, and percentages; determining co-references; and marking relationships among different elements such as employee of, product of, location of, etc.…”

A Framework for Extracting Biological Relations from Different Resources

“…The supervised approach is to train the system over a large manually tagged corpus, where the system can apply machine learning techniques to generate extraction patterns [5]. This approach has typically been applied to small corpora such as a collection of news wire stories, and has difficulty scaling to the Web.…”