University of Massachusetts: MUC-4 test results and analysis
نویسندگان
چکیده
The UMass/MUC-4 system is based on a form of sentence analysis known as selective concept extraction . This approach to language processing is distinguished by a minimal reliance on syntactic sentenc e analysis, along with a minimal dictionary customized to operate in a limited domain . Last year, the UMass/MUC-3 system demonstrated the viability of selective concept extraction, but serious questions were raised about th e portability and scalability of the technology, particularly with respect to the creation of domain-dependent and taskdependent dictionaries . We estimated that 9 person/months went into the creation of the dictionary used by UMass/MUC-3, and we were unable to say how much domain-dependent lexicon was still missing . We were nevertheless sure that our dictionary coverage was incomplete .
منابع مشابه
University of Massachusetts: MUC-3 test results and analysis
We believe that the score reports we obtained for TST2 provide an accurate assessment of ou r system's capabilities insofar as they are consistent with the results of our own internal tests conducted near the end of phase 2 . . The required TST2 score reports indicate that our system achieved the highest combined scores for recall (51%) and precision (62%) as well as the highest recall score of...
متن کاملDescription of the UMass system as used for MUC-6
Information extraction research at the University of Massachusetts is based on portable, trainable language processing components. Some components are more effective than others, some have been under development longer than others, but in all cases, we are working to eliminate manual knowledge engineering. Although UMass has participated in previous MUC evaluations, all of our information extra...
متن کاملNew York University PROTEUS system: MUC-4 test results and analysis
Evaluating the degree of improvement over the MUC-3 runs is complicated by the changes between MUC-3 an d MUC-4: there were changes in the template structure, the MURDER templates were eliminated, content mappin g constraints were incorporated into the scoring program, and the rules for manual remapping were much more con strained. We resumed system development specifically for MUC (with regula...
متن کاملUniversity of Massachusetts: description of the CIRCUS system as used for MUC-4
CIRCUS uses no syntactic grammar and produces no parse tree as it analyzes a sentence . Rather, it uses lexically-indexed syntactic knowledge to segment incoming text into noun phrases, prepositional phrases, and ver b phrases. These constituents are stored in global buffers that track the subjects, verbs, direct objects, and prepositiona l phrases of a sentence. Because we restrict the buffer ...
متن کامل