[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/aclbulk-2009-korkontzelos-detecting-compositionality-multi-word-expressions/) [home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [English](https://md.mova.elamur.ai/free/en/docs/papers/en/) / Detecting Compositionality in Multi-Word Expressions # Detecting Compositionality in Multi-Word Expressions **Authors:** Ioannis Korkontzelos, Suresh Manandhar · **Year:** 2009 · **Venue:** Proceedings of the ACL-IJCNLP 2009 Conference Short Papers **Link:** [aclanthology.org/P09-2017](https://aclanthology.org/P09-2017/) · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) — summary only [**26** citations](https://openalex.org/works?filter=cites:W2147955622) openalex · 2026-10-18[**9** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/aclbulk-2009-korkontzelos-detecting-compositionality-multi-word-expressions/) of the 140673 papers whose bibliographies we read[Proceedings of the ACL-IJCNLP 2009 Conference Short Papers](https://aclanthology.org/volumes/P09-2/)[licence](https://creativecommons.org/licenses/by-nc-sa/3.0/) - [Publisher's page](https://aclanthology.org/P09-2017/) - [PDF](https://aclanthology.org/P09-2017.pdf) - [DOI 10.3115/1667583.1667605](https://doi.org/10.3115/1667583.1667605) - [OpenAlex](https://openalex.org/W2147955622) **Authors (2)** 1. [Ioannis Korkontzelos](https://openalex.org/A5060320466) [ORCID](https://orcid.org/0000-0001-8052-2471) · h 20 · 1468 citations · 101 works 2. [Suresh Manandhar](https://openalex.org/A5108193412) h 30 · 7364 citations · 141 works Citations and author metrics from openalex (2026-10-18); authors with the same name are not always told apart. ## What it is about The paper decides whether a multi-word expression (MWE) is compositional, that is, whether its meaning follows from its parts. The focus is compound nominals, proper names and adjective-noun constructions. For each MWE the method collects the context words of the expression and of its parts from a corpus, builds a graph of their co-occurrence, and clusters it to induce senses. It keeps only the major senses. The only language-dependent parts are a part-of-speech tagger and a parser. Because no compositionality test set existed, the authors built one from the 52,217 MWEs of WordNet 3.0, with a semi-automatic step to aid annotation. The best setting reaches 68.42% accuracy for detecting non-compositional MWEs, above a one-cluster baseline. The similarity measure Jsn beats Jc in every setting. ## Ideas - I1. A cheap check in `onto/src/wsd.rs` before any sense induction: for each EWT compound, measure the overlap between the context words of the whole and those of its head. Label it compositional when the overlap is high. Measure: accuracy on a hand-checked sample of 200 WordNet MWEs, two identical runs. - I2. Put compositionality into `en/src/lexgen.rs` as a flag on each compound row, filled only from the one-cluster baseline first. Measure: the number of compound readings the noun-noun rule adds on EWT, with and without the flag. - I3. Build a small compositionality set from WordNet multi-word lexemes the way the paper does, as a test set only. The WordNet data is open, but the judgments are the authors' and must be checked by hand. Measure: agreement with a second annotator on 50 items. ## For Mova The chapter is [19. The lexicon: vocabulary, multiword expressions and register](https://md.mova.elamur.ai/free/en/docs/languages/en/19-lexicon-mwe-register/). The code is `onto/src/wsd.rs` (the context step) and `en/src/lexgen.rs` (the flag). Sense induction is not CPU-cheap in its full form, so I1 is the first step to measure. The paper's numbers are for WordNet MWEs and not for EWT. ## Cite The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.3115/1667583.1667605](https://doi.org/10.3115/1667583.1667605) ``` @inproceedings{korkontzelos2009detecting, title = {{Detecting Compositionality in Multi-Word Expressions}}, author = {Korkontzelos, Ioannis and Manandhar, Suresh}, booktitle = {Proceedings of the ACL-IJCNLP 2009 Conference Short Papers}, year = {2009}, doi = {10.3115/1667583.1667605}, url = {https://doi.org/10.3115/1667583.1667605} } ``` - [← previous Automatic training of lemmatization rules that handle morphological changes in pre-, in- and suffixes alike](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2009-jongejan-automatic-training-lemmatization-rules-that/) - [next → Multi-word expressions in textual inference: Much ado about nothing?](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2009-marneffe-multi-word-expressions-textual-inference/) - [↑ back to English](https://md.mova.elamur.ai/free/en/docs/papers/en/) ## References 17 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. E. Agirre and A. Soroa. 2007. Semeval-2007, task 02: Evaluating WSI and discrimination systems. In proceedings of SemEval-2007. ACL. [find](https://scholar.google.com/scholar?q=E%2E+Agirre+and+A%2E+Soroa%2E+2007%2E+Semeval%2D2007%2C+task+02%3A+Evaluating+WSI+and+discrimination+systems%2E+In+proceedings+of+SemEval%2D2007%2E+ACL%2E) 2. E. Agirre, D. Martı́nez, O. de Lacalle, and A. Soroa. 2006. Two graph-based algorithms for state-of-the-art WSD. In proceedings of EMNLP-2006. ACL. [find](https://scholar.google.com/scholar?q=E%2E+Agirre%2C+D%2E+Mart%C4%B1%CC%81nez%2C+O%2E+de+Lacalle%2C+and+A%2E+Soroa%2E+2006%2E+Two+graph%2Dbased+algorithms+for+state%2Dof%2Dthe%2Dart+WSD%2E+In+proceedings+of+EMNLP%2D2006%2E+ACL%2E) 3. T. Baldwin, C. Bannard, T. Tanaka, and D. Widdows. 2003. An empirical model of MWE decomposability. In proceedings of the MWE workshop. ACL. [find](https://scholar.google.com/scholar?q=T%2E+Baldwin%2C+C%2E+Bannard%2C+T%2E+Tanaka%2C+and+D%2E+Widdows%2E+2003%2E+An+empirical+model+of+MWE+decomposability%2E+In+proceedings+of+the+MWE+workshop%2E+ACL%2E) 4. T. Baldwin. 2006. Compositionality and MWEs: Six of one, half a dozen of the other? In proceedings of the MWE workshop. ACL. [find](https://scholar.google.com/scholar?q=T%2E+Baldwin%2E+2006%2E+Compositionality+and+MWEs%3A+Six+of+one%2C+half+a+dozen+of+the+other%3F+In+proceedings+of+the+MWE+workshop%2E+ACL%2E) 5. C. Bannard, T. Baldwin, and A. Lascarides. 2003. A statistical approach to the semantics of verb-particles. In proceedings of the MWE workshop. ACL. [find](https://scholar.google.com/scholar?q=C%2E+Bannard%2C+T%2E+Baldwin%2C+and+A%2E+Lascarides%2E+2003%2E+A+statistical+approach+to+the+semantics+of+verb%2Dparticles%2E+In+proceedings+of+the+MWE+workshop%2E+ACL%2E) 6. C. Biemann. 2006. Chinese whispers - an efficient graph clustering algorithm and its application to NLP problems. In proceedings of TextGraphs. ACL. [find](https://scholar.google.com/scholar?q=C%2E+Biemann%2E+2006%2E+Chinese+whispers+%2D+an+efficient+graph+clustering+algorithm+and+its+application+to+NLP+problems%2E+In+proceedings+of+TextGraphs%2E+ACL%2E) 7. T. Brants and A. Franz. 2006. Web 1t 5-gram corpus, version 1. Technical report, Google Research. [find](https://scholar.google.com/scholar?q=T%2E+Brants+and+A%2E+Franz%2E+2006%2E+Web+1t+5%2Dgram+corpus%2C+version+1%2E+Technical+report%2C+Google+Research%2E) 8. P. Cook, A. Fazly, and S. Stevenson. 2008. The VNC-Tokens Dataset. In proceedings of the MWE workshop. ACL. [find](https://scholar.google.com/scholar?q=P%2E+Cook%2C+A%2E+Fazly%2C+and+S%2E+Stevenson%2E+2008%2E+The+VNC%2DTokens+Dataset%2E+In+proceedings+of+the+MWE+workshop%2E+ACL%2E) 9. T. Dunning. 1993. Accurate methods for the statistics of surprise and coincidence. Computational Linguistics, 19(1):61–74. [find](https://scholar.google.com/scholar?q=T%2E+Dunning%2E+1993%2E+Accurate+methods+for+the+statistics+of+surprise+and+coincidence%2E+Computational+Linguistics%2C+19%281%29%3A61%E2%80%9374%2E) 10. G. Katz and E. Giesbrecht. 2006. Automatic identification of non-compositional MWEs using latent semantic analysis. In proceedings of the MWE workshop. ACL. [find](https://scholar.google.com/scholar?q=G%2E+Katz+and+E%2E+Giesbrecht%2E+2006%2E+Automatic+identification+of+non%2Dcompositional+MWEs+using+latent+semantic+analysis%2E+In+proceedings+of+the+MWE+workshop%2E+ACL%2E) 11. I. P. Klapaftis and S. Manandhar. 2008. WSI using graphs of collocations. In proceedings of ECAI-2008. [find](https://scholar.google.com/scholar?q=I%2E+P%2E+Klapaftis+and+S%2E+Manandhar%2E+2008%2E+WSI+using+graphs+of+collocations%2E+In+proceedings+of+ECAI%2D2008%2E) 12. D. Klein and C. Manning. 2003. Fast exact inference with a factored model for natural language parsing. In proceedings of NIPS 15. MIT Press. [find](https://scholar.google.com/scholar?q=D%2E+Klein+and+C%2E+Manning%2E+2003%2E+Fast+exact+inference+with+a+factored+model+for+natural+language+parsing%2E+In+proceedings+of+NIPS+15%2E+MIT+Press%2E) 13. I. Korkontzelos, I. Klapaftis, and S. Manandhar. 2009. Graph connectivity measures for unsupervised parameter tuning of graph-based sense induction systems. In proceedings of the UMSLLS Workshop, NAACL HLT 2009. [find](https://scholar.google.com/scholar?q=I%2E+Korkontzelos%2C+I%2E+Klapaftis%2C+and+S%2E+Manandhar%2E+2009%2E+Graph+connectivity+measures+for+unsupervised+parameter+tuning+of+graph%2Dbased+sense+induction+systems%2E+In+proceedings+of+the+UMSLLS+Workshop%2C+NAAC) 14. L. Lee. 1999. Measures of distributional similarity. In proceedings of ACL. [find](https://scholar.google.com/scholar?q=L%2E+Lee%2E+1999%2E+Measures+of+distributional+similarity%2E+In+proceedings+of+ACL%2E) 15. D. McCarthy, B. Keller, and J. Carroll. 2003. Detecting a continuum of compositionality in phrasal verbs. In proceedings of the MWE workshop. ACL. [find](https://scholar.google.com/scholar?q=D%2E+McCarthy%2C+B%2E+Keller%2C+and+J%2E+Carroll%2E+2003%2E+Detecting+a+continuum+of+compositionality+in+phrasal+verbs%2E+In+proceedings+of+the+MWE+workshop%2E+ACL%2E) 16. G. A. Miller. 1995. WordNet: a lexical database for English. ACM, 38(11):39–41. [find](https://scholar.google.com/scholar?q=G%2E+A%2E+Miller%2E+1995%2E+WordNet%3A+a+lexical+database+for+English%2E+ACM%2C+38%2811%29%3A39%E2%80%9341%2E) [our card](https://md.mova.elamur.ai/free/en/docs/papers/lex-1994-miller-wordnet/) 17. D. Yarowsky. 1995. Unsupervised WSD rivaling supervised methods. In proceedings of ACL. [find](https://scholar.google.com/scholar?q=D%2E+Yarowsky%2E+1995%2E+Unsupervised+WSD+rivaling+supervised+methods%2E+In+proceedings+of+ACL%2E)