--- title: "Automatic Interpretation of Noun Compounds Using WordNet Similarity — Kim 2005" description: "The paper interprets a novel binary noun compound, such as \"paper submission\", by finding the most similar… 21 references, cited by 32 papers here." authors: ["Su Nam Kim", "Timothy Baldwin"] year: 2005 venue: "Second International Joint Conference on Natural Language Processing: Full Papers" source: "https://aclanthology.org/I05-1082/" doi: "10.1007/11562214_82" licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/kim-2005-automatic-interpretation-noun-compounds-wordnet/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/kim-2005-automatic-interpretation-noun-compounds-wordnet/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2005](https://md.research.elamur.ai/free/en/papers/2005/) / Automatic Interpretation of Noun Compounds Using WordNet Similarity # Automatic Interpretation of Noun Compounds Using WordNet Similarity **Authors:** [Su Nam Kim](https://md.research.elamur.ai/free/en/authors/su-nam-kim/) and [Timothy Baldwin](https://md.research.elamur.ai/free/en/authors/timothy-baldwin/) · **Year:** 2005 · **Venue:** Second International Joint Conference on Natural Language Processing (IJCNLP 2005) **Link:** [aclanthology.org/I05-1082](https://aclanthology.org/I05-1082/) · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) — summary only [**102** citations](https://openalex.org/works?filter=cites:W1540103129) OpenAlex, 2026-10-14 · **32** citations in our library of the 140,884 papers whose bibliographies we read · [Second International Joint Conference on Natural Language Processing: Full Papers](https://aclanthology.org/volumes/I05-1/) · [licence](https://creativecommons.org/licenses/by-nc-sa/3.0/) - [Publisher's page](https://aclanthology.org/I05-1082/) - [PDF](https://aclanthology.org/I05-1082.pdf) - [DOI 10.1007/11562214_82](https://doi.org/10.1007/11562214_82) - [OpenAlex](https://openalex.org/W1540103129) **Authors (2)** 1. [Su Nam Kim](https://openalex.org/A5110283311) [Semantic Scholar](https://www.semanticscholar.org/author/1736741380) · h 18 · 2,164 citations · 51 works 2. [Timothy Baldwin](https://openalex.org/A5103085805) [ORCID](https://orcid.org/0000-0002-4445-1386) · [Semantic Scholar](https://www.semanticscholar.org/author/145465286) · h 54 · 12,068 citations · 411 works Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart. ## What it is about The paper interprets a novel binary noun compound, such as "paper submission", by finding the most similar training compound and copying its semantic relation. Similarity between the two nouns comes from WordNet::Similarity, with four measures compared. The relation set has 20 members, and the data is noun compounds from the Penn Treebank Wall Street Journal: 1,088 training and 1,081 test instances. The best measure, WUP, classifies 53.3% of the test compounds correctly. That is above the 43.0% majority baseline and at the level of the 52.3% inter-annotator agreement. The authors also expect the modifier and the head noun to carry different weight for different relations (for TIME, the modifier), and they test that with a weight parameter. ## Ideas - I3. Before measuring, count the share of binary compounds in the EWT test set. The paper reports 88.4% binary in the WSJ, and that share sets the scope. Measure: the share, reported with the first result. ## For Mova - I1. Nearest-compound classifier in `onto/src/wsd.rs` with WordNet path similarity between modifier and head synsets, copying the relation of the nearest training compound. Measure: accuracy on EWT noun compounds against the majority-class baseline, two identical runs. - I2. Relation-specific weight between modifier and head (the alpha of the paper) in `en/src/explain.rs`, fitted on a split. Measure: accuracy on the held-out split, with one weight versus a weight per relation. The chapter is [languages/en/18-compounding-conversion-minor.md](https://mova.elamur.ai/free/en/docs/languages/en/18-compounding-conversion-minor/). The code is `onto/src/wsd.rs` and `en/src/explain.rs`. The WSJ material is licensed Penn Treebank data, so it is a test only, and the paper is NC; the 20-relation set is a design source, not something to copy into a release. ## Institutions [🎓**The University of Melbourne** Melbourne · Australia 47 works · 19,957 citations](https://md.research.elamur.ai/free/en/universities/the-university-of-melbourne/) · [🎓**University of Illinois Chicago** Chicago · United States 28 works · 18,688 citations](https://md.research.elamur.ai/free/en/universities/university-of-illinois-chicago/) · [🔬**Data61** Sydney · Australia 9 works · 2,187 citations](https://md.research.elamur.ai/free/en/labs/data61/) ## Cite Cite as Su Nam Kim and Timothy Baldwin. 2005. Automatic Interpretation of Noun Compounds Using WordNet Similarity. Second International Joint Conference on Natural Language Processing: Full Papers. The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.1007/11562214_82](https://doi.org/10.1007/11562214_82) ```bibtex @inproceedings{kim2005automatic, title = {{Automatic Interpretation of Noun Compounds Using WordNet Similarity}}, author = {Su Nam Kim and Timothy Baldwin}, booktitle = {Second International Joint Conference on Natural Language Processing: Full Papers}, year = {2005}, doi = {10.1007/11562214\_82}, url = {https://doi.org/10.1007/11562214_82} } ``` - [← previous Evaluating Machine Translation Output with Automatic Sentence Segmentation](https://md.research.elamur.ai/free/en/papers/matusov-2005-evaluating-machine-translation-output-automatic/) - [next → Arabic Diacritization Using Weighted Finite-State Transducers](https://md.research.elamur.ai/free/en/papers/nelken-2005-arabic-diacritization-weighted-finite-state/) - [↑ back to papers of 2005](https://md.research.elamur.ai/free/en/papers/2005/) ## References 21 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Cao, Y., Li, H.: Base noun phrase translation using web data and the em algorithm. In: COLING2002. (2002) [find](https://scholar.google.com/scholar?q=Cao%2C+Y%2E%2C+Li%2C+H%2E%3A+Base+noun+phrase+translation+using+web+data+and+the+em+algorithm%2E+In%3A+COLING2002%2E+%282002%29) 2. Baldwin, T., Tanaka, T.: Translation by machine of compound nominals: Getting it right. In: ACL2004-MWE, Barcelona, Spain (2004) 24–31 ’correct.percent’ ’incorrect.percent’ THRESHOLD Similarity=0.57 Error 0.4 0.6 0.8 (similarity) [find](https://scholar.google.com/scholar?q=Baldwin%2C+T%2E%2C+Tanaka%2C+T%2E%3A+Translation+by+machine+of+compound+nominals%3A+Getting+it+right%2E+In%3A+ACL2004%2DMWE%2C+Barcelona%2C+Spain+%282004%29+24%E2%80%9331+%E2%80%99correct%2Epercent%E2%80%99+%E2%80%99incorrect%2Epercent%E2%80%99+THRESHOLD+Similarity%3D0%2E57+E) 3. Lauer, M.: Designing Statistical Language Learners: Experiments on Noun Compounds. PhD thesis, Macquarie University (1995) [find](https://scholar.google.com/scholar?q=Lauer%2C+M%2E%3A+Designing+Statistical+Language+Learners%3A+Experiments+on+Noun+Compounds%2E+PhD+thesis%2C+Macquarie+University+%281995%29) 4. Lapata, M.: The disambiguation of nominalizations. Comput. Linguist. 28 (2002) 357–388 [find](https://scholar.google.com/scholar?q=Lapata%2C+M%2E%3A+The+disambiguation+of+nominalizations%2E+Comput%2E+Linguist%2E+28+%282002%29+357%E2%80%93388) 5. Finin, T.W.: The semantic interpretation of compound nominals. PhD thesis, University of Illinois, Urbana, Illinois, USA (1980) [find](https://scholar.google.com/scholar?q=Finin%2C+T%2EW%2E%3A+The+semantic+interpretation+of+compound+nominals%2E+PhD+thesis%2C+University+of+Illinois%2C+Urbana%2C+Illinois%2C+USA+%281980%29) 6. Vanderwende, L.: Algorithm for automatic interpretation of noun sequences. In: Proceedings of the 15th conference on Computational linguistics. (1994) 782–788 [find](https://scholar.google.com/scholar?q=Vanderwende%2C+L%2E%3A+Algorithm+for+automatic+interpretation+of+noun+sequences%2E+In%3A+Proceedings+of+the+15th+conference+on+Computational+linguistics%2E+%281994%29+782%E2%80%93788) 7. Rosario, B., Marti, H.: Classifying the semantic relations in noun compounds via a domain-specific lexical hierarchy. In: Proceedings of the 2001 Conference on Empirical Methods in Natural Language Processing. (2001) 82–90 [our card](https://md.research.elamur.ai/free/en/papers/rosario-2001-classifying-semantic-relations-noun-compounds/) 8. Moldovan, D., Badulescu, A., Tatu, M., Antohe, D., Girju, R.: Models for the semantic classification of noun phrases. HLT-NAACL 2004: Workshop on Computational Lexical Semantics (2004) 60–67 [find](https://scholar.google.com/scholar?q=Moldovan%2C+D%2E%2C+Badulescu%2C+A%2E%2C+Tatu%2C+M%2E%2C+Antohe%2C+D%2E%2C+Girju%2C+R%2E%3A+Models+for+the+semantic+classification+of+noun+phrases%2E+HLT%2DNAACL+2004%3A+Workshop+on+Computational+Lexical+Semantics+%282004%29+60%E2%80%9367) 9. Fan, J., Barker, K., Porter, B.W.: The knowledge required to interpret noun compounds. In: Seventh International Joint Conference on Artificial Intelligence. (2003) 1483–1485 [find](https://scholar.google.com/scholar?q=Fan%2C+J%2E%2C+Barker%2C+K%2E%2C+Porter%2C+B%2EW%2E%3A+The+knowledge+required+to+interpret+noun+compounds%2E+In%3A+Seventh+International+Joint+Conference+on+Artificial+Intelligence%2E+%282003%29+1483%E2%80%931485) 10. Barker, K., Szpakowicz, S.: Semi-automatic recognition of noun modifier relationships. In: Proceedings of the 17th international conference on Computational linguistics. (1998) 96– 102 [find](https://scholar.google.com/scholar?q=Barker%2C+K%2E%2C+Szpakowicz%2C+S%2E%3A+Semi%2Dautomatic+recognition+of+noun+modifier+relationships%2E+In%3A+Proceedings+of+the+17th+international+conference+on+Computational+linguistics%2E+%281998%29+96%E2%80%93+102) 11. Artiles, J., Penas, A., Verdejo, F.: Word sense disambiguation based on term to term similarity in a context space. In: Senseval-3: Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text. (2004) 58–63 [find](https://scholar.google.com/scholar?q=Artiles%2C+J%2E%2C+Penas%2C+A%2E%2C+Verdejo%2C+F%2E%3A+Word+sense+disambiguation+based+on+term+to+term+similarity+in+a+context+space%2E+In%3A+Senseval%2D3%3A+Third+International+Workshop+on+the+Evaluation+of+Systems+for+the+Se) 12. Patwardhan, S., Banerjee, S., Pedersen, T.: Using measures of semantic relatedness for word sense disambiguation. In: Proceedings of the Fourth International Conference on Intelligent Text Processing and Computational Linguistics. (2003) [find](https://scholar.google.com/scholar?q=Patwardhan%2C+S%2E%2C+Banerjee%2C+S%2E%2C+Pedersen%2C+T%2E%3A+Using+measures+of+semantic+relatedness+for+word+sense+disambiguation%2E+In%3A+Proceedings+of+the+Fourth+International+Conference+on+Intelligent+Text+Processing+) 13. Resnik, P.: Disambiguating noun groupings with respect to wordnet senses. In: Proceedings of the 3rd Workship on Very Large Corpus. (1995) 77–98 [find](https://scholar.google.com/scholar?q=Resnik%2C+P%2E%3A+Disambiguating+noun+groupings+with+respect+to+wordnet+senses%2E+In%3A+Proceedings+of+the+3rd+Workship+on+Very+Large+Corpus%2E+%281995%29+77%E2%80%9398) 14. Wu, Z., Palmer, M.: Verb semantics and lexical selection. In: 32nd. Annual Meeting of the Association for Computational Linguistics. (1994) 133 –138 [our card](https://md.research.elamur.ai/free/en/papers/wu-1994-verb-semantics-lexical-selection/) 15. Fellbaum, C., ed.: WordNet: An Electronic Lexical Database. MIT Press, Cambridge, USA (1998) [find](https://scholar.google.com/scholar?q=Fellbaum%2C+C%2E%2C+ed%2E%3A+WordNet%3A+An+Electronic+Lexical+Database%2E+MIT+Press%2C+Cambridge%2C+USA+%281998%29) 16. Leacock, C., Chodorow, N.: Combining local context and wordnet similarity for word sense identification. [15] [find](https://scholar.google.com/scholar?q=Leacock%2C+C%2E%2C+Chodorow%2C+N%2E%3A+Combining+local+context+and+wordnet+similarity+for+word+sense+identification%2E+%5B15%5D) 17. Jiang, J., Conrath, D.: Semantic similarity based on corpus statistics and lexical taxonomy. In: Proceedings on International Conference on Research in Computational Linguistics. (1998) 19–33 [find](https://scholar.google.com/scholar?q=Jiang%2C+J%2E%2C+Conrath%2C+D%2E%3A+Semantic+similarity+based+on+corpus+statistics+and+lexical+taxonomy%2E+In%3A+Proceedings+on+International+Conference+on+Research+in+Computational+Linguistics%2E+%281998%29+19%E2%80%9333) 18. Lin, D.: An information-theoretic definition of similarity. In: Proceedings of the International Conference on Machine Learning. (1998) [find](https://scholar.google.com/scholar?q=Lin%2C+D%2E%3A+An+information%2Dtheoretic+definition+of+similarity%2E+In%3A+Proceedings+of+the+International+Conference+on+Machine+Learning%2E+%281998%29) 19. Banerjee, S., Pedersen, T.: Extended gloss overlaps as a measure of semantic relatedness. In: Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence. (2003) 805–810 [our card](https://md.research.elamur.ai/free/en/papers/banerjee-2003-extended-gloss-overlaps-as-measure/) 20. Levi, J.: The syntax and semantics of complex nominals. In: New York:Academic Press. (1979) [find](https://scholar.google.com/scholar?q=Levi%2C+J%2E%3A+The+syntax+and+semantics+of+complex+nominals%2E+In%3A+New+York%3AAcademic+Press%2E+%281979%29) 21. Downing, P.: On the creation and use of English compound nouns. Language 53 (1977) 810–42 [find](https://scholar.google.com/scholar?q=Downing%2C+P%2E%3A+On+the+creation+and+use+of+English+compound+nouns%2E+Language+53+%281977%29+810%E2%80%9342)