Abstract
Grammatically incorrect sentences result either from an unknown (possibly misspelled) word, an incorrect word order or even an omitted / redundant word. Sentences with these errors are a bottle-neck to NLP systems because they cannot be parsed correctly. Human beings are able to overcome this problem (either occurring in spoken or written language) since they are capable of doing a semantic similarity search to find out if a similar utterance has been heard before or a syntactic similarity search for a stored utterance that shares structural similarities with the input. If the syntactic and semantic analysis of the rest of the input can be done correctly, then a ‘gap’ that exists in the utterance, can be uniquely identified. In this paper, a system named SAUCOLA which is based on a concept lattice, that mimics human skills in resolving knowledge gaps that exist in written language is presented. The preliminary results show that correct stored sentences can be retrieved based on the words contained in the incorrect input sentence.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cardie, C.: Embedded machine learning systems for natural language processing: A general framework. LNAI 1040. Springer (1996) 315–328
Carpineto, C., Romano, G.: GALOIS: An order-theoretic approach to conceptual clustering. Procs. of ICML’93. Morgan Kaufmann (1993) 33–40
Carpineto, C., Romano, G.: A lattice conceptual clustering systems and its application to browsing retrieval. Machine Learning 24 (1996a) 95–122
Carpineto, C., Romano, G.: Information retrieval through hybrid navigation of lattice representations. Journal of Human-Computer Studies 45 (1996b) 553–578
Collins, B., Cunningham, P.: Adaptation-guided retrieval in EBMT: A case based approach to machine translation. Procs. of EWCBR’96. LNAI 1168. Springer (1996) 91–104
Daelemans, W.: Memory-based lexical acquisition and processing. Procs. of EAMT Workshop. LNAI 898. Springer (1995) 85–98
Daelemans, W., van den Bosch, A., and Weijters, T.: Empirical learning of natural language processing tasks. Procs. of ECML’97. LNAI 1224. Springer (1997) 337–344
Demiroz, G., Guvenir, H. A.: Classification by voting feature intervals. Procs. of ECML’97. LNAI 1224. Springer (1997) 85–92
Ellis, G.: Efficient retrieval from hierarchies of objects using lattice operations. Procs. of ICCS’93. LNAI 699. Springer (1993) 274–293
Godin, R., Missiaoui, R., April, A.: Experimental comparison of navigation in a Galois lattice with conventional information retrieval methods. Journal of Man-Machine Studies 38 (1993) 747–767
Kaneda S., Almuallim, H., Akiba, Y., Ishii, M., Kawaoka, T.: A revision learner to acquire selection rules from human made rules and examples. LNAI 1040. Springer (1996) 439–452
Knight, K., Chander, I., Haines, M., Hatzivassiloglou, V., Hovy E., Iida M., Luk, S. K., Wjiteney, R., Yamada, K.: Filling knowledge gaps in a broad based coverage machine translation system. Procs. of IJCAI’95 (1995) 1390–1396
Maarek, Y. S., Berry, D. M., Kaiser, G. E.: An information retrieval approach for automatically constructing software libraries. IEEE Transactions on Software Engineering 17(8) (1991) 800–813
Nagao, M.: A Framework for a mechanical translation between Japanese and English by analogy principle. In Elithorn, A. and Manerji, R. (eds): Artificial and Human Intelligence. Elsevier Publishers (1984) B.V. NATO
Nirenburg, S. (ed.): The PANGLOSS Mark III machine translation system. CMU-CMT-95-145 (1995) Joint Technical Report
Oosthuizen, G. D.: The use of a lattice in knowledge processing. Ph.D. Thesis (1988) University of Strathclyde, Glasgow
Serutla, L., Oosthuizen, G. D.: Using a lattice to enhance adaptation-guided retrieval in example based machine translation. Procs. of SAICSIT’97 (1997) 177–191
Wettschereck, D.: A hybrid nearest-neighbour and nearest-hyperrectangle algorithm. Procs. of ECML’94. LNAI 784. Springer (1994) 323–335
Yamada S., Nakaiwa, H., Ogura, K., Ikehara, S.: A method of automatically adapting MT system to different domains. Procs. of TMI’95 (1995) 303–310
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Serutla, L., Kourie, D. (1998). Sentence Analysis Using a Concept Lattice. In: Farwell, D., Gerber, L., Hovy, E. (eds) Machine Translation and the Information Soup. AMTA 1998. Lecture Notes in Computer Science(), vol 1529. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49478-2_21
Download citation
DOI: https://doi.org/10.1007/3-540-49478-2_21
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65259-5
Online ISBN: 978-3-540-49478-2
eBook Packages: Springer Book Archive