12 Hits in 6.2 sec

SRI International

Jerry R. Hobbs
1991 Proceedings of the 3rd conference on Message understanding - MUC3 '91  
We developed a preprocessor for MUC-2 and modified it for MUC-3 . Our relevance filter was develope d for MUC-3, as was our current template-generation component .  ...  The original purpose of TACITUS was to aid us in investigating the problems of inferencing in natura l language .  ...  ACKNOWLEDGEMENT S This research has been funded by the Defense Advanced Research Projects Agency under Office of Nava l Research contracts N00014-85-C-0013 and N00014-90-C-0220 .  ... 
doi:10.3115/1071958.1071991 dblp:conf/muc/Hobbs91a fatcat:uz7gpdy6dfajpdd7zxjz5tbkcu

FASTUS: A Cascaded Finite-State Transducer for Extracting Information from Natural-Language Text [article]

Jerry R. Hobbs, Douglas Appelt, John Bear, David Israel, Megumi Kameyama, Mark Stickel, and Mabry Tyson (Artificial Intelligence Center, SRI International, Menlo Park, California)
1997 arXiv   pre-print
This decomposition of language processing enables the system to do exactly the right amount of domain-independent syntax, so that domain-dependent semantic and pragmatic processing can be applied to the  ...  FASTUS is a system for extracting information from natural language text for entry into a database and for other applications.  ...  Acknowledgments The FASTUS system was originally built under SRI internal research and development funding.  ... 
arXiv:cmp-lg/9705013v1 fatcat:bhyuziqt75eyfjgqv4hr5cibu4

Computational aspects of discourse in the context of MUC-3

Lucja Iwańska, Douglas Appelt, Damaris Ayuso, Kathy Dahlgren, Bonnie Glover Stalls, Ralph Grishman, George Krupka, Christine Montgomery, Ellen Riloff
1991 Proceedings of the 3rd conference on Message understanding - MUC3 '91  
. 4 If the description includes an existing module not used for MUC-3, then a brief explanation as to why it was not used i s given .  ...  UMASS' CIRCUS : CONSOLIDATIO N The UMass system (see [24] and our system summary in these proceedings) as used for MUC-3 is compose d of a conceptual sentence analyzer, CIRCUS [23] , and a discourse  ... 
doi:10.3115/1071958.1071998 dblp:conf/muc/IwanskaAADSGKMR91 fatcat:boqdsdo73zepbic3w2hjpfdj5i

Text filtering in MUC-3 and MUC-4

David D. Lewis, Richard M. Tong
1992 Proceedings of the 4th conference on Message understanding - MUC4 '92  
Acknowledgments We thank DARPA for supporting the authors' travel to the MUC-4 workshop, and Beth Sundheim for her aid with this paper and her splendid handling of the MUC-4 process.  ...  SRI: SRI's TACITUS system fielded for MUC-3 used both pre-parse and post-parse filtering. The pre-parse filter was a two-stage function.  ...  Table 3 similarly presents the values of the F-measure [van79] for all MUC-3 and MUC-4 systems.  ... 
doi:10.3115/1072064.1072069 dblp:conf/muc/LewisT92 fatcat:6nl63dsr55dlln5bqa4nhepzpa

Information extraction: beyond document retrieval

Robert Gaizauskas, Yorick Wilks
1998 Journal of Documentation  
Here we describe the nature of the IE task, review the history of the area from its origins in AI work in the 1960's and 70's till the present, discuss the techniques being used to carry out the task,  ...  describe application areas where IE systems are or are about to be at work, and conclude with a discussion of the challenges facing the area.  ...  Acknowledgments Thanks to Beth Sundheim of the US Naval Command, Control, and Ocean Surveillance Center RDT\&E Division (NRaD) for detailed comments during the preparation of this paper.  ... 
doi:10.1108/eum0000000007162 fatcat:diexgodbeng4lh6kfrn4kylrfm

Relating Templates to Language and Logic [chapter]

John F. Sowa
1999 Lecture Notes in Computer Science  
As a result, the template-filling operations of IE become part of a more general set of operations that can be used in various combinations to process knowledge of any kind, including linguistic knowledge  ...  But many of the most successful programs for information extraction (IE) are based on domain-dependent templates that ignore the details at the center of attention of the major theories of syntax and semantics  ...  The canonical formation rules of generalization, specialization, and equivalence can be used to characterize all three approaches to language processing that were discussed in Section 1:  ... 
doi:10.1007/3-540-48089-7_5 fatcat:qgxyjjekx5aaxehzso2pdqjjli

Text-Mining: Application Development Challenges [chapter]

Sundar Varadarajan, Kas Kasravi, Ronen Feldman
2003 Applications and Innovations in Intelligent Systems X  
Special emphasis is placed on post-information extraction processing, such as improving the relevance of the extracted information, summarization models, techniques for handling typographical errors, resolution  ...  Lastly, the paper discusses various utilities to help with the development of a text-mining application, such as feature analysis, visualization, database connectivity, source document pre-processing,  ...  Specifically, full parsing was included in the SRI TACITUS system (implemented for MUC-3) [3, 4] and the NYU PROTEUS system (implemented for MUC-6) [1] .  ... 
doi:10.1007/978-1-4471-0649-4_17 fatcat:ruq2vvv5xzbxtp5xl3bpuncjr4

Mining the Biomedical Literature in the Genomic Era: An Overview

Hagit Shatkay, Ronen Feldman
2003 Journal of Computational Biology  
most relevant and useful for specific analysis tasks.  ...  During the last few years, there was a surge of interest in using the biomedical literature, (e.  ...  ACKNOWLEDGMENTS We thank the ClearForest-Celera team for their work towards the KDD-cup 2002. HS thanks Stephen Edwards, Mark Boguski, and John Wilbur for their collaboration on the GenTheme project.  ... 
doi:10.1089/106652703322756104 pmid:14980013 fatcat:vbwcpl66ujhqdgq4wdjtllbg5e

Sémiotique textuelle et contenu linguistique

Marc Cavazza
1996 Intellectica Revue de l Association pour la Recherche Cognitive  
A major issue for the development of humanities computing technologies is to determine the proper relationships between form and content in semiotic objects.  ...  In this paper, we review some current conceptions of semantic content description in the framework of textual semiotics.  ...  It was for profit and not for pleasure that Lady Tamplin was so anxious for the company of her dear cousin. 'It is as well you are in France', said Van Aldin.  ... 
doi:10.3406/intel.1996.1531 fatcat:tohc5d7etfektammucqceveft4

A Study of Chinese Named Entity and Relation Identification in a Specific Domain [article]

Tianfang Yao, Universität Des Saarlandes, Universität Des Saarlandes
We have proposed a three-stage pipeline computational model for the error correction of word segmentation and POS tagging, NE recognition and NER identification.  ...  This thesis aims at investigating automatic identification of Chinese named entities (NEs) and their relations (NERs) in a specific domain.  ...  He has supported me in exploring the field of Information Extraction for Chinese throughout my thesis work.  ... 
doi:10.22028/d291-25846 fatcat:3pdjlvoo4bdb5bdyrscpbsrgjy

Summarizing Text for Intelligent Communication (Dagstuhl Seminar 9350)

Brigitte Endres-Niggermeyer, Jerry Hobbs, Karen Sparck Jones
Due to cost reasons. this report has been divided up into a short version (with a higher number of copies), a quite lenghty volume for the participants, and an electronic version contammg all material.  ...  The research was supported by ARPA s TIPSTER Initiative. Acknowledgements The work reported herein would not have been possible without the fine efforts of Woojin Paik.  ...  Acknowledgements The work reported herein would not have been possible without the ne efforts of Woojin Paik, Mary McKenna, Ken McVearry, Edmund Yu, and Carin Obad.  ... 
doi:10.4230/dagsemrep.79 fatcat:fnfn472ubfgfvow2lzvgigo2vi

Summarizing Text for Intelligent Communication Dagstuhl Seminar

B Endressniggemeyer, J Hobbs, K Jones
1993 unpublished
References In my view, text summarizing presupposes a thorough understanding of the text, which, to a certain extent, will result in text interpretation.  ...  Sundheim, 1991; MUC 3 Proceedings, 1991; MUC 4 Proceedings, 1992] .  ...  subset from the data base (3) the automatic generation of a surmnary out of a subset of relevant information using a text generation system. he system used for this purpose -SPOKESMAN -has also been applied  ...