W. Lehnert
ABSTRACT
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 sentence 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 the portability and scalability of the technology, particularly with respect to the creation of domain-dependent and task-dependent 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.
- Cardie, C. (1992a) "Corpus-Based Acquisition of Relative Pronoun Disambiguation Heuristics" to appear in Proceedings of the 30th Annual Conference of the Association of Computational Linguisitcs. University of Delaware, Newark DE. Google Scholar
Digital Library
- Cardie, C. (1992b) "Learning to Disambiguate Relative Pronouns" to appear in Proceedings of the Tenth National Conference on Artificial Intelligence. San Jose, CA.Google Scholar
- Cardie, C. (1992c) "Using Cognitive Biases to Guide Feature Set Selection" to appear in Proceedings, Fourteenth Annual Conference of the Cognitive Science Society, University of Indiana, Bloomington, IA.Google Scholar
- Fisher, D. and Riloff, E. (1992) "Applying Statistical Methods to Small Corpora: Benefiting from a Limited Domain" to appear in Probabilistic Approaches to Natural Language, a AAAI Fall Symposium. Cambridge, MA.Google Scholar
- Riloff, E. and Lehnert, W. (1992) "Classifying Texts Using Relevancy Signatures" to appear in Proceedings of the Tenth National Conference on Artificial Intelligence. San Jose, CA.Google Scholar
Recommendations
NLP and text analysis at the University of Massachusetts
HLT '91: Proceedings of the workshop on Speech and Natural LanguageOur group is investigating a variety of techniques centered around the use of text corpora to support natural language processing applications. We are interested in information extraction from text, text classification, and knowledge acquisition from ...
Dublin city university at CLEF 2004: experiments in monolingual, bilingual and multilingual retrieval
CLEF'04: Proceedings of the 5th conference on Cross-Language Evaluation Forum: multilingual Information Access for Text, Speech and ImagesThe Dublin City University group participated in the monolingual, bilingual and multilingual retrieval tasks. The main focus of our investigation for CLEF 2004 was extending our information retrieval system to document languages other than English, and ...
University of Massachusetts: description of the CIRCUS system as used for MUC-4
MUC4 '92: Proceedings of the 4th conference on Message understandingCIRCUS is a conceptual analyzer that produces semantic case frame representations for input sentences. Although space does not permit us to give a full technical description of CIRCUS, we will attempt to convey some sense of sentence analysis via ...
Comments