This Article 
 Bibliographic References 
 Add to: 
A Parallel System for Text Inference Using Marker Propagations
August 1998 (vol. 9 no. 8)
pp. 729-747

Abstract—This paper presents a possible solution for the text inference problem—extracting information unstated in a text, but implied. Text inference is central to natural language applications such as information extraction and dissemination, text understanding, summarization, and translation. Our solution takes advantage of a semantic English dictionary available in electronic form that provides the basis for the development of a large linguistic knowledge base. The inference algorithm consists of a set of highly parallel search methods that, when applied to the knowledge base, find contexts in which sentences are interpreted. These contexts reveal information relevant to the text. Implementation, results, and parallelism analysis are discussed.

[1] R. Alterman, "Event Concept Coherence," Semantic Structures, Advances in Natural Language Processing, D.L. Waltz, ed., pp. 57-87.Hillsdale, N.J.: Lawrence Erlbaum Associates, 1989.
[2] E. Brill, "A Simple Rule-Based Part of Speech Tagger," Proc. Third Conf. Applied Natural Language Processing, pp. 152-155, 1992.
[3] R. Bruce and J. Wiebe, "Word-Sense Disambiguation Using Decomposable Models," Proc. 32nd Ann. Meeting Assoc. Computational Linguistics,Las Cruces, N.M., 1994.
[4] K.W. Church and P. Hanks, "Word Association Norms, Mutual Information and Lexicography," Computational Linguistics, vol. 16, no. 1, pp. 22-29, 1990.
[5] E. Charniak, "Passing Markers: A Theory of Contextual Influence in Language Comprehension," Cognitive Science, vol. 7, pp. 171-190, 1983.
[6] E. Charniak, "A Neat Theory of Marker Passing," Proc. Fifth Nat'l Conf. Artificial Intelligence AAAI-86, pp. 584-588, 1986.
[7] E. Charniak and R. Goldman, "A Semantic for Probabilstic Quantifier-Free First-Order Languages, with Particular Application to Story Understanding," Proc. 11th Int'l Joint Conf. Artificial Intelligence IJCAI-89, pp. 1,074-1,079, 1989.
[8] P.R. Cohen and C.L. Loiselle, "Beyond ISA: Structures for Plausible Inference in Semantic Networks," Proc. Seventh Nat'l Conf. Artificial Intelligence AAAI-88, pp. 415-420, 1988.
[9] S. Fahlman, NETL: A System for Representing and Using Real-World Knowledge.Cambridge, Mass.: The MIT Press, 1979.
[10] C.J. Fillmore, "The Case for Case," Universals in Linguistic Theory, E. Bach and R. Harms, eds., pp. 1-88.New York: Holt, Rinehart and Winston, 1968.
[11] A. Gupta, Parallelism in Production Systems.Los Altos, Calif.: Morgan Kaufmann, 1987.
[12] S. Harabagiu and D. Moldovan, "A Parallel Algorithm for Text Inference," Proc. Int'l Parallel Processing Symp., pp. 441-445, 1996.
[13] S. Harabagiu, "WordNet-Based Inference of Textual Context, Cohesion and Coherence," PhD thesis, Univ. of Southern California, Los Angeles, 1997.
[14] J. Hendler, Integrating Marker-Passing and Problem-Solving.Hillsdale, N.J.: Lawrence Erlbaum Associates, 1988.
[15] J. Hobbs, M. Stickel, D. Appelt, and P. Martin, "Interpretation as Abduction," Artificial Intelligence, vol. 63, pp. 69-142, 1993.
[16] M.P. Marcus, B. Santorini, and M.A. Marcinkiewicz, "Building a Large Annotated Corpus of English: The Penn Treebank," Computational Linguistics, vol. 20, no. 2, 1993, pp. 313-330. Reprinted inUsing Large Corpora,Susan Armstrong, ed., MIT Press, Cambridge, Mass., 1994, pp. 273-290.
[17] G.A. Miller, "WordNet: A Lexical Database," Comm. ACM, vol. 38: no. 11, pp. 39-41, Nov. 1995.
[18] D. Moldovan, W. Lee, and C Lin, "Snap: A Marker-Propagation Architecture for Knowledge Processing," IEEE Trans. Parallel and Distributed Systems, vol. 3, pp. 1-13, 1992.
[19] S. McRoy, "Using Multiple Knowledge Sources for Word Sense Discrimination," Computational Linguistics, vol. 18, pp. 1-30, 1992.
[20] H. Tou Ng and H. Lee, "Integrating Multiple Knowledge Sources to Disambiguate Word Sense: An Exemplar-Based Approach," Proc. 34th Ann. Meeting Assoc. Computational Linguistics, pp. 40-47,Santa Cruz, Calif., 1996.
[21] P. Norvig, "Marker Passing as a Weak Method for Text Inferencing," Cognitive Science, vol. 13, pp. 569-620, 1989.
[22] M.R. Quillian, "Semantic Memory," PhD thesis, Carnegie Inst. of Technology, Carnegie Mellon Univ., Pittsburg, Penn., 1966.
[23] A. Ratnaparkhi, "A Maximum Entropy Model for Part-of-Speech Tagging," Proc. Conf. Empirical Methods in Natural Language Processing, Univ. of Pennsylvania, 1996.
[24] R. Schank, "Language and Memory. Principles," Readings in Natural Language Processing, B. Grosz and K. Spark-Jones, eds., pp. 171-192. Morgan Kaufmann, 1986.
[25] B.M. Sundheim, "TIPSTER/MUC-5 Information Extraction System Evaluation," Proc. Fifth Message Understanding Conf., pp. 27-44,Baltimore, 1993.
[26] D.L. Waltz, "Massively Parallel AI," Proc. Nat'l Conf. Artificial Intelligence AAAI-90,Boston, 1990.
[27] R. Wilensky, Planning and Understanding: A Computational Approach to Human Reasoning.Reading, Mass.: Addison-Wesley, 1983.
[28] Y.A. Wilks, B.M. Slator, and L.M. Guthrie, Electric Words—Dictionaries, Computers and Meanings.Cambridge, Mass.: The MIT Press, 1996.
[29] D. Yarowsky, "Unsupervised Word Sense Disambiguation Rivaling Supervised Methods," Proc. 33rd Ann. Meeting Assoc. ComputationalLinguistics, 1995, pp.189-196.
[30] Y.H. Yu and R.F. Simmons, "Truly Parallel Understanding of Text," Proc. Eighth Nat'l Conf. Artificial Intelligence AAAI-80, pp. 996-1,001, 1990.

Index Terms:
Parallel search algorithms, parallel knowledge processing, marker propagations, natural language understanding, parallel inference, metrics for parallelism analysis, speed-up.
Sanda M. Harabagiu, Dan I. Moldovan, "A Parallel System for Text Inference Using Marker Propagations," IEEE Transactions on Parallel and Distributed Systems, vol. 9, no. 8, pp. 729-747, Aug. 1998, doi:10.1109/71.706046
Usage of this product signifies your acceptance of the Terms of Use.