[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
Selection and information: a class-based approach to lexical relationships
Publisher:
  • University of Pennsylvania
  • Computer and Information Science Dept. 2000 South 33rd St. Philadelphia, PA
  • United States
Order Number:UMI Order No. GAX94-13894
Reflects downloads up to 21 Dec 2024Bibliometrics
Skip Abstract Section
Abstract

Selectional constraints are limitations on the applicability of predicates to arguments. For example, the statement "The number two is blue" may be syntactically well formed, but at some level it is anomalous-- scBLUE is not a predicate that can be applied to numbers.

In this dissertation, I propose a new, information-theoretic account of selectional constraints. Unlike previous approaches, this proposal requires neither the identification of primitive semantic features nor the formalization of complex inferences based on world knowledge. The proposed model assumes instead that lexical items are organized in a conceptual taxonomy according to class membership, where classes are defined simply as sets--that is, extensionally, rather than in terms of explicit features or properties. Selection is formalized in terms of a probabilistic relationship between predicates and concepts: the selectional behavior of a predicate is modeled as its distributional effect on the conceptual classes of its arguments, expressed using the information-theoretic measure of relative entropy. The use of relative entropy leads to an illuminating interpretation of what selectional constraints are: the strength of a predicate's selection for an argument is identified with the quantity of information it carries about that argument.

In addition to arguing that the model is empirically adequate, I explore its application to two problems. The first concerns a linguistic question: why some transitive verbs permit implicit direct objects ("John ate $\emptyset$") and others do not ("*John brought $\emptyset$"). It has often been observed informally that the omission of objects is connected to the ease with which the object can be inferred. I have made this observation more formal by positing a relationship between inferability and selectional constraints, and have confirmed the connection between selectional constraints and implicit objects in a set of computational experiments.

Second, I have explored the practical applications of the model in resolving syntactic ambiguity. A number of authors have recently begun investigating the use of corpus-based lexical statistics in automatic parsing; the results of computational experiments using the present model suggest that often lexical relationships are better viewed in terms of underlying conceptual relationships such as selectional preference and concept similarity. Thus the information-theoretic measures proposed here can serve not only as components in a theory of selectional constraints, but also as tools for practical natural language processing.

Cited By

  1. Menai M (2014). Word sense disambiguation using evolutionary algorithms - Application to Arabic language, Computers in Human Behavior, 41:C, (92-103), Online publication date: 1-Dec-2014.
  2. Séaghdha D and Korhonen A Modelling selectional preferences in a lexical hierarchy Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation, (170-179)
  3. Fernandez-Amoros D and Heradio R (2011). Understanding the role of conceptual relations in Word Sense Disambiguation, Expert Systems with Applications: An International Journal, 38:8, (9506-9516), Online publication date: 1-Aug-2011.
  4. Zhou G, Zhao J, Liu K and Cai L Exploiting web-derived selectional preference to improve statistical dependency parsing Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1, (1556-1565)
  5. Hajnicz E Similarity-Based method of detecting diathesis alternations in semantic valence dictionary of polish verbs Proceedings of the 2011 international conference on Security and Intelligent Information Systems, (345-358)
  6. McCarthy D Measuring similarity of word meaning in context with lexical substitutes and translations Proceedings of the 12th international conference on Computational linguistics and intelligent text processing - Volume Part I, (238-252)
  7. Fallucchi F and Zanzotto F (2011). Inductive probabilistic taxonomy learning using singular value decomposition, Natural Language Engineering, 17:1, (71-94), Online publication date: 1-Jan-2011.
  8. Girju R and Paul M (2011). Modeling reciprocity in social interactions with probabilistic latent space models, Natural Language Engineering, 17:1, (1-36), Online publication date: 1-Jan-2011.
  9. Shutova E, Sun L and Korhonen A Metaphor identification using verb and noun clustering Proceedings of the 23rd International Conference on Computational Linguistics, (1002-1010)
  10. Pitler E, Bergsma S, Lin D and Church K Using web-scale N-grams to improve base NP parsing performance Proceedings of the 23rd International Conference on Computational Linguistics, (886-894)
  11. McGillivray B Automatic selectional preference acquisition for Latin verbs Proceedings of the ACL 2010 Student Research Workshop, (73-78)
  12. Shutova E Models of metaphor in NLP Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, (688-697)
  13. Séaghdha D Latent variable models of selectional preference Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, (435-444)
  14. Fan J, Ferrucci D, Gondek D and Kalyanpur A PRISMATIC Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading, (122-127)
  15. Baumer E, White J and Tomlinson B Comparing semantic role labeling with typed dependency parsing in computational metaphor identification Proceedings of the NAACL HLT 2010 Second Workshop on Computational Approaches to Linguistic Creativity, (14-22)
  16. Shutova E Automatic metaphor interpretation as a paraphrasing task Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, (1029-1037)
  17. Hajnicz E The EM-based wordnet synsets annotation of NP/PP heads Proceedings of the 4th conference on Human language technology: challenges for computer science and linguistics, (423-434)
  18. Van Durme B, Michalak P and Schubert L Deriving generalized knowledge from corpora using WordNet abstraction Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics, (808-816)
  19. ACM
    Navigli R (2009). Word sense disambiguation, ACM Computing Surveys (CSUR), 41:2, (1-69), Online publication date: 1-Feb-2009.
  20. Blazquez-del-Toro J, Fisteus J, Centeno V and Sanchez-Fernandez L (2008). A semantic similarity measure in the context of semantic queries, International Journal of Computer Applications in Technology, 33:4, (285-291), Online publication date: 1-Jan-2009.
  21. McGillivray B, Johansson C and Apollon D Semantic structure from correspondence analysis Proceedings of the 3rd Textgraphs Workshop on Graph-Based Algorithms for Natural Language Processing, (49-52)
  22. Blanchard E, Harzallah M and Kuntz P A generic framework for comparing semantic similarities on a subsumption hierarchy Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence, (20-24)
  23. ACM
    Iida R, Inui K and Matsumoto Y (2007). Zero-anaphora resolution by learning rich syntactic pattern features, ACM Transactions on Asian Language Information Processing (TALIP), 6:4, (1-22), Online publication date: 1-Dec-2007.
  24. Ponzetto S and Strube M (2007). Knowledge derived from wikipedia for computing semantic relatedness, Journal of Artificial Intelligence Research, 30:1, (181-212), Online publication date: 1-Sep-2007.
  25. McInnes B, Pedersen T and Pakhomov S Determining the syntactic structure of medical terms in clinical notes Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing, (9-16)
  26. Van de Cruys T and Moirón B Semantics-based multiword expression extraction Proceedings of the Workshop on a Broader Perspective on Multiword Expressions, (25-32)
  27. Zanzotto F, Pennacchiotti M and Pazienza M Discovering asymmetric entailment relations between verbs using selectional preferences Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics, (849-856)
  28. Pazienza M, Pennacchiotti M and Zanzotto F Discovering verb relations in corpora Proceedings of the 19th international conference on Advances in Applied Artificial Intelligence: industrial, Engineering and Other Applications of Applied Intelligent Systems, (1042-1052)
  29. Pekar V Acquisition of verb entailment from text Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, (49-56)
  30. Pekar V Discovery of Entailment Relations from Event Co-Occurrences Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy, (516-520)
  31. Nakov P and Hearst M Using the web as an implicit training set Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, (835-842)
  32. ACM
    Beitzel S, Jensen E, Frieder O, Grossman D, Lewis D, Chowdhury A and Kolcz A Automatic web query classification using labeled and unlabeled training data Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval, (581-582)
  33. Nakov P and Hearst M Search engine statistics beyond the n-gram Proceedings of the Ninth Conference on Computational Natural Language Learning, (17-24)
  34. Tsang V and Stevenson S Using selectional profile distance to detect verb alternations Proceedings of the HLT-NAACL Workshop on Computational Lexical Semantics, (30-37)
  35. Lapata M and Brew C (2004). Verb class disambiguation using informative priors, Computational Linguistics, 30:1, (45-73), Online publication date: 1-Mar-2004.
  36. Mason Z (2004). CorMet, Computational Linguistics, 30:1, (23-44), Online publication date: 1-Mar-2004.
  37. Weeds J and Weir D A general framework for distributional similarity Proceedings of the 2003 conference on Empirical methods in natural language processing, (81-88)
  38. Hovy E, Philpot A, Klavans J, Germann U, Davis P and Popper S Extending metadata definitions by automatically extracting and organizing glossary definitions Proceedings of the 2003 annual national conference on Digital government research, (1-6)
  39. Thompson C and Mooney R (2003). Acquiring word-meaning mappings for natural language interfaces, Journal of Artificial Intelligence Research, 18:1, (1-44), Online publication date: 1-Jan-2003.
  40. Buckeridge A and Sutcliffe R Disambiguating noun compounds with latent semantic indexing COLING-02 on COMPUTERM 2002: second international workshop on computational terminology - Volume 14, (1-7)
  41. ACM
    Alfonseca E A WordNet interface to APL2 Proceedings of the 2002 conference on APL: array processing languages: lore, problems, and applications, (7-16)
  42. ACM
    Alfonseca E (2019). A WordNet interface to APL2, ACM SIGAPL APL Quote Quad, 32:4, (7-16), Online publication date: 1-Jun-2002.
  43. Li H (2019). Word clustering and disambiguation based on co-occurrence data, Natural Language Engineering, 8:1, (25-42), Online publication date: 1-Mar-2002.
  44. Clark S and Weir D Class-based probability estimation using a semantic hierarchy Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies, (1-8)
  45. Maedche A and Staab S (2001). Ontology Learning for the Semantic Web, IEEE Intelligent Systems, 16:2, (72-79), Online publication date: 1-Mar-2001.
  46. Kietz J, Volz R and Maedche A Extracting a domain-specific ontology from a corporate intranet Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7, (167-175)
  47. im Walde S Clustering verbs semantically according to their alternation behaviour Proceedings of the 18th conference on Computational linguistics - Volume 2, (747-753)
  48. Clark S and Weir D A class-based probabilistic approach to structural disambiguation Proceedings of the 18th conference on Computational linguistics - Volume 1, (194-200)
  49. McCarthy D Using semantic preferences to identify verbal participation in role switching alternations Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference, (256-263)
  50. Rooth M, Riezler S, Prescher D, Carroll G and Beil F Inducing a semantically annotated lexicon via EM-based clustering Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics, (104-111)
  51. Cunningham H (2018). A definition and short history of Language Engineering, Natural Language Engineering, 5:1, (1-16), Online publication date: 1-Mar-1999.
  52. McMahon J and Smith F (1998). A Review of Statistical Language Processing Techniques, Artificial Intelligence Review, 12:5, (347-391), Online publication date: 1-Oct-1998.
  53. Klavans J and Kan M Role of verbs in document analysis Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 1, (680-686)
  54. Barker K and Szpakowicz S Semi-automatic recognition of noun modifier relationships Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 1, (96-102)
  55. Wu H, de Paiva Alves E and Furugori T Structural disambiguation based on reliable estimation of strength of association Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 2, (1416-1422)
  56. Mccarthy D (1998). The Balancing Act, Judith L. Klavans and Philip Resnik, Journal of Logic, Language and Information, 7:2, (223-227), Online publication date: 1-Apr-1998.
  57. Ide N and Véronis J (1998). Introduction to the special issue on word sense disambiguation, Computational Linguistics, 24:1, (2-40), Online publication date: 1-Mar-1998.
  58. Assadi H Knowledge acquisition from texts Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics, (504-506)
  59. Briscoe T and Carroll J Automatic extraction of subcategorization from corpora Proceedings of the fifth conference on Applied natural language processing, (356-363)
  60. ACM
    Smeaton A and Quigley I Experiments on using semantic distances between words in image caption retrieval Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval, (174-180)
  61. McMahon J and Smith F (1996). Improving statistical language model performance with automatically generated word hierarchies, Computational Linguistics, 22:2, (217-247), Online publication date: 1-Jun-1996.
  62. Agarwal R Evaluation of semantic clusters Proceedings of the 33rd annual meeting on Association for Computational Linguistics, (284-286)
  63. Lauer M Corpus statistics meet the noun compound Proceedings of the 33rd annual meeting on Association for Computational Linguistics, (47-54)
  64. Ribas F On learning more appropriate Selectional Restrictions Proceedings of the seventh conference on European chapter of the Association for Computational Linguistics, (112-118)
  65. Magerman D (1995). Review of "Statistical language learning" by Eugene Charniak. The MIT Press 1993., Computational Linguistics, 21:1, (103-111), Online publication date: 1-Mar-1995.
  66. Jacquemin C Recycling terms into a partial parser Proceedings of the fourth conference on Applied natural language processing, (113-118)
  67. Brill E and Resnik P A rule-based approach to prepositional phrase attachment disambiguation Proceedings of the 15th conference on Computational linguistics - Volume 2, (1198-1204)
  68. Knight K and Luk S Building a large-scale knowledge base for machine translation Proceedings of the Twelfth AAAI National Conference on Artificial Intelligence, (773-778)
  69. ACM
    Jacquemin C (1994). A temporal connectionist approach to natural language, ACM SIGART Bulletin, 5:3, (12-22), Online publication date: 1-Jul-1994.
  70. Wu Z and Palmer M Verbs semantics and lexical selection Proceedings of the 32nd annual meeting on Association for Computational Linguistics, (133-138)
  71. Yarowsky D Decision lists for lexical ambiguity resolution Proceedings of the 32nd annual meeting on Association for Computational Linguistics, (88-95)
  72. Hearst M Multi-paragraph segmentation of expository text Proceedings of the 32nd annual meeting on Association for Computational Linguistics, (9-16)
Contributors
  • University of Maryland, College Park

Index Terms

  1. Selection and information: a class-based approach to lexical relationships
    Please enable JavaScript to view thecomments powered by Disqus.

    Recommendations