Corpus Statistics Meet the Noun Compound: Some Empirical Results

What it is about

The paper applies the Hindle and Rooth idea of corpus association to noun compounds: which bracketing of a three-noun compound, left or right, is correct. Two models are compared: an adjacency model, which uses neighbouring nouns, and a dependency model, which uses the head-modifier structure. Several training schemes are tried, with word and concept associations. The test set has 244 compounds that received a parse, taken from an 8-million-word encyclopedia corpus, and the training data had those test compounds removed. The dependency model reaches 77.5% against 68.9% for adjacency, a difference the paper reports as significant at the 5% level for the pattern training scheme. The best tuned technique reaches 81%, against a 67% baseline. Left-branching compounds make up 67% of the test set.

Ideas

• I1. Bracketing decision for en/src/parse.rs: for EWT noun-noun runs with two nouns of a compound or nmod chain, score the left and right bracketing with head-modifier counts. Measure: accuracy on EWT test compound arcs against the 67% left-branching baseline, two identical runs.
• I2. Use the left-branching prior as the first baseline in en explain, and only then the count model. Measure: the gain of counts over the prior on EWT, reported by the explanation step.
• I3. Concept back-off through onto (WordNet hypernyms) for nouns not seen in the counts. Measure: accuracy on held-out compounds whose nouns are unseen, with and without the back-off.

For Mova

The chapter is 18. Compounding, conversion and the minor processes, with 22. Phrases: noun, adjective, adverb and prepositional phrases for the bracketing. The code is en/src/parse.rs (the candidate choice) and onto/src/wsd.rs (concept back-off). The paper's data is an encyclopedia corpus, not Mova data; any figure must come from EWT test.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.3115/981658.981665

@inproceedings{lauer1995corpus,
  title = {{Corpus Statistics Meet the Noun Compound: Some Empirical Results}},
  author = {Lauer, Mark},
  booktitle = {33rd Annual Meeting of the Association for Computational Linguistics},
  year = {1995},
  doi = {10.3115/981658.981665},
  url = {https://doi.org/10.3115/981658.981665}
}

References

25 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Arens, Y., Granacki, J. and Parker, A. 1987. Phrasal Analysis of Long Noun Sequences. In Proceedings of the 25th Annual Meeting of the Association for Computational Linguistics, Stanford, CA. pp59-64. find
2. Brent, Michael. 1993. From Grammar to Lexicon: Unsupervised Learning of Lexical Syntax. In Computational Linguistics, Vol 19(2), Special Issue on Using Large Corpora II, pp243-62. find
3. Brill, Eric. 1993. A Corpus-based Approach to Language Learning. PhD Thesis, University of Pennsylvania, Philadelphia, PA.. find
4. Charniak, Eugene. 1993. Statistical Language Learning. MIT Press, Cambridge, MA. find
5. Finin, Tim. 1980. The Semantic Interpretation of Compound Nominals. PhD Thesis, Co-ordinated Science Laboratory, University of Illinois, Urbana, IL. find
6. Hindle, D. and Rooth, M. 1993. Structural Ambiguity and Lexical Relations. In Computational Linguistics Vol. 19(1), Special Issue on Using Large Corpora I, ppl03-20. find
7. Isabelle, Pierre. 1984. Another Look At Nominal Compounds. In Proceedings of COLING-84, Stanford, CA. pp509-16. find
8. Karp, D., Schabes, Y., Zaidel, M. and Egedi, D. 1992. A Freely Available Wide Coverage Morphological Analyzer for English. In Proceedings of COLING-92, Nantes, France, pp950-4. find
9. Kobayasi, Y., Tokunaga, T. and Tanaka, H. 1994. Analysis of Japanese Compound Nouns using Collocational Information. In Proceedings of COLING-94, Kyoto, Japan, pp865-9. find
10. Lauer, Mark. 1994. Conceptual Association for Compound Noun Analysis. In Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics, Student Session, Las Cruces, NM. pp337-9. find
11. Lauer, M. and Dras, M. 1994. A Probabilistic Model of Compound Nouns. In Proceedings of the 7th Australian Joint Conference on Artificial Intelligence, Armidale, NSW, Australia. World Scientific Press, pp474-81. find
12. Leonard, Rosemary. 1984. The Interpretation of English Noun Sequences on the Computer. North-Holland, Amsterdam. find
13. Levi, Judith. 1978. The Syntax and Semantics of Complex Nominals. Academic Press, New York. find
14. Liberman, M. and Sproat, R. 1992. The Stress and Structure of Modified Noun Phrases in English. In Sag, I. and Szabolcsi, A., editors, Lexical Matters CSLI Lecture Notes No. 24. University of Chicago Press, ppl31-81. find
15. Marcus, Mit~.hell. 1980. A Theory of Syntactic Recognition for Natural Language. MIT Press, Cambridge, MA. find
16. McDonald, David B. 1982. Understanding Noun Compounds. PhD Thesis, Carnegie-Mellon University, Pittsburgh, PA. find
17. Pustejovsky, J., Bergler, S. and Anick, P. 1993. Lexical Semantic Techniques for Corpus Analysis. In Computational Linguistics Vol 19(2), Special Issue on Using Large Corpora II, pp331-58. find
18. Resnik, Philip. 1993. Selection and Information: A Class.Based Approach to Lexical Relationships. PhD dissertation, University of Pennsylvania, Philadelphia, PA. find
19. Resnik, P. and Hearst, M. 1993. Structural Ambiguity and Conceptual Relations. In Proceedings of the Workshop on Very Large Corpora: Academic and Industrial Perspectives, June 22, Ohio State University, pp58-64. find
20. Ryder, Mary Ellen. 1994. Ordered Chaos: The Interpretation of English Noun-Noun Compounds. University of California Press Publications in Linguistics, Vol 123. find
21. Smadja, Frank. 1993. Retrieving Collocations from Text: Xtract. In Computational Linguistics, Vol 19(1), Special Issue on Using Large Corpora I, pp143-177. find
22. Sparck Jones, Karen. 1 9 8 3 . Compound Noun Interpretation Problems. In Fallside, F. and Woods, W.A., editors, Computer Speech Processing. Prentice-Hall, NJ. pp363-81. find
23. Sproat, Richard. 1994. English noun-phrase accent prediction for text-to-speech. In Computer Speech and Language, Vol 8, pp79-94. find
24. Vanderwende, Lucy. 1993. SENS: The System for Evaluating Noun Sequences. In Jensen, K., Heidorn, G. and Richardson, S., editors, Natural Language Processing: The PLNLP Approach. Kluwer Academic, pp161-73. ter Stal, Wilco. 1995. Syntactic Disambiguation of Nominal Compounds Using Lexical and Conceptu… find
25. Yarowsky, David. 1992. Word-Sense Disambiguation Using Statistical Models of Roget's Categories Trained on Large Corpora. In Proceedings of COLING-92, Nantes, France, pp454-60. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-1995-lauer-corpus-statistics-meet-noun-compound/