---
title: "Literal and Metaphorical Sense Identification — Turney 2011"
description: "The paper addresses telling apart literal and metaphorical uses of a word in context, which matters for textual entailment and the applications built on…"
authors: ["Peter Turney", "Yair Neuman", "Dan Assaf", "Yohai Cohen"]
year: 2011
venue: "Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D11-1063/"
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/turney-2011-literal-metaphorical-sense-identification-through/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/turney-2011-literal-metaphorical-sense-identification-through/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2011](https://md.research.elamur.ai/free/en/papers/2011/) / Literal and Metaphorical Sense Identification through Concrete and Abstract Context

# Literal and Metaphorical Sense Identification through Concrete and Abstract Context

**Authors:** [Peter Turney](https://md.research.elamur.ai/free/en/authors/peter-turney/), Yair Neuman, Dan Assaf, Yohai Cohen · **Year:** 2011 · **Venue:** Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/D11-1063/) · [PDF](https://aclanthology.org/D11-1063.pdf) · [OpenAlex](https://openalex.org/W2252218513)

**Citations:** 238 citations (openalex-snapshot · 2026-10-14) · [156](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
The paper addresses telling apart literal and metaphorical uses of a word in context, which matters for textual entailment and the applications built on it. Earlier work treated this as standard word sense disambiguation. The authors instead draw on cognitive linguistics, where metaphor carries knowledge from concrete source domains into abstract target domains. Their hypothesis is that the more abstract a word's surroundings are, the more likely the word is used metaphorically.

They first build an automatic abstractness scorer. Each word is compared, through an LSA-style vector space built from a large web corpus, with sets of abstract and concrete "paradigm" words, and the paradigm words are selected using MRC Psycholinguistic Database ratings. They then turn the abstractness of context words into features for logistic regression.

Tests on adjective–noun phrases and on the TroFi Example Base give state-of-the-art or comparable results. Because the features describe only the context, the classifier also works on verbs it never saw in training.

## Key points
- **Abstractness scorer:**
  - Score = summed similarity to 20 abstract paradigm words minus summed similarity to 20 concrete ones, rescaled to the 0–1 range.
  - Trained on half of the 4,295 MRC-rated words and tested on the other half, where it reaches a correlation of 0.81 with the human ratings.
- **Semantic space:**
  - About 5×10¹⁰ words of university web text, indexed with Wumpus.
  - Vocabulary of 114,501 WordNet terms.
  - Word–context matrix weighted with PPMI and reduced with truncated SVD, following Rapp's approach.
- **Adjective experiment:** 100 adjective–noun phrases labeled denotative or connotative by five annotators. The classifier reaches 79% average accuracy (e.g., *deep snow* vs. *deep appreciation*).
- **TroFi experiments:** 50 verbs in 3,737 sentences from the 1987–89 WSJ corpus.
  - With one model per verb (Birke and Sarkar's setup), average f-score is 63.9%, versus their 64.9%.
  - With a single model trained on 25 new verbs and tested on the 25 original, unseen verbs, average f-score is 68.1%.
- **Feature weights:** In the logistic regression, average noun abstractness (excluding proper nouns) has by far the largest weight, about 11.4. Adding the target word's own abstractness gave no significant gain, probably because the targets span a narrow abstractness range.

## Interesting ideas
- **Paradigm-word scoring:** A word can be rated on any semantic scale by comparing it with two small sets of anchor words. Here the anchors are picked with a supervised method from a human-rated lexicon rather than chosen by hand. The same recipe could produce lexicons for other dimensions or other languages, as long as some seed ratings exist.
- **Context-only features:** Describing only the context, and never the target word, makes the classifier independent of the target. One model can then cover unseen words, which saves collecting labeled data for every word of interest.
- **Unseen-word evaluation:** Training on one set of verbs and testing on a disjoint set is a demanding check of generalization. It is worth copying wherever a method claims to transfer across lexical items.
- **Theory-driven features:** A cognitive-linguistics claim (concrete-to-abstract transfer) is turned into a small set of interpretable features. The regression weights then show which part of speech in the context carries the signal, here mainly nouns.
- **Swapping the rating source:** The authors note the same scorer could be trained on MRC imagability ratings instead of abstractness. This could serve tasks such as image retrieval or image annotation, showing how one rating pipeline can be reused for different psycholinguistic properties.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

Topics: [Word sense disambiguation](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/)

## Cited by

Cited by

156 papers of our library cite it (of the 140884 whose bibliographies we read); 7 of them have a page here, 149 not yet.

- [Distributional Semantics in Technicolor](https://md.research.elamur.ai/free/en/papers/bruni-2012-distributional-semantics-technicolor/)
- [The Pragmatics behind Politics: Modelling Metaphor, Framing and Emotion in Political Discourse](https://md.research.elamur.ai/free/en/papers/cabot-2020-pragmatics-behind-politics-modelling-metaphor/)
- [A Dataset for Metaphor Detection in Early Medieval Hebrew Poetry](https://md.research.elamur.ai/free/en/papers/eacl-2024-toker-dataset-metaphor-detection-early-medieval/)
- [Combining Language and Vision with a Multimodal Skip-gram Model](https://md.research.elamur.ai/free/en/papers/lazaridou-2015-combining-language-vision-multimodal-skip/)
- [Metaphor as a Medium for Emotion: An Empirical Study](https://md.research.elamur.ai/free/en/papers/mohammad-2016-metaphor-as-medium-emotion-empirical/)
- [Black Holes and White Rabbits: Metaphor Identification with Visual Features](https://md.research.elamur.ai/free/en/papers/shutova-2016-black-holes-white-rabbits-metaphor/)
- [Metaphor Detection with Cross-Lingual Model Transfer](https://md.research.elamur.ai/free/en/papers/tsvetkov-2014-metaphor-detection-cross-lingual-model/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{turney2011literal,
  title = {{Literal and Metaphorical Sense Identification through Concrete and Abstract Context}},
  author = {Turney, Peter and Neuman, Yair and Assaf, Dan and Cohen, Yohai},
  booktitle = {Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing},
  year = {2011},
  url = {https://aclanthology.org/D11-1063/}
}
```

- [← previous Linguistically Motivated Complementizer Choice in Surface Realization](https://md.research.elamur.ai/free/en/papers/rajkumar-2011-linguistically-motivated-complementizer-choice-surface/)
- [next → MEANT: An inexpensive, high-accuracy, semi-automatic metric for evaluating translation utility based on semantic roles](https://md.research.elamur.ai/free/en/papers/lo-2011-meant-inexpensive-high-accuracy-semi/)
- [↑ back to papers of 2011](https://md.research.elamur.ai/free/en/papers/2011/)

## References

29 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Julia Birke and Anoop Sarkar. 2006. A clustering approach for the nearly unsupervised recognition of non-literal language. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2006), pages 329– 336. [find](https://scholar.google.com/scholar?q=Julia+Birke+and+Anoop+Sarkar%2E+2006%2E+A+clustering+approach+for+the+nearly+unsupervised+recognition+of+non%2Dliteral+language%2E+In+Proceedings+of+the+11th+Conference+of+the+European+Chapter+of+the+Associat)
2. Julia Birke and Anoop Sarkar. 2007. Active learning for the identification of nonliteral language. In Proceedings of the Workshop on Computational Approaches to Figurative Language at HLT/NAACL-07, pages 21–28. [find](https://scholar.google.com/scholar?q=Julia+Birke+and+Anoop+Sarkar%2E+2007%2E+Active+learning+for+the+identification+of+nonliteral+language%2E+In+Proceedings+of+the+Workshop+on+Computational+Approaches+to+Figurative+Language+at+HLT%2FNAACL%2D07%2C+pa)
3. Stefan Büttcher and Charles Clarke. 2005. Efficiency vs. effectiveness in terabyte-scale information retrieval. In Proceedings of the 14th Text REtrieval Conference (TREC 2005), Gaithersburg, MD. [find](https://scholar.google.com/scholar?q=Stefan+Bu%CC%88ttcher+and+Charles+Clarke%2E+2005%2E+Efficiency+vs%2E+effectiveness+in+terabyte%2Dscale+information+retrieval%2E+In+Proceedings+of+the+14th+Text+REtrieval+Conference+%28TREC+2005%29%2C+Gaithersburg%2C+MD%2E)
4. John Caron. 2001. Experiments with LSA scoring: Optimal rank and basis. In Proceedings of the SIAM Computational Information Retrieval Workshop, pages 157–169, Raleigh, NC. [find](https://scholar.google.com/scholar?q=John+Caron%2E+2001%2E+Experiments+with+LSA+scoring%3A+Optimal+rank+and+basis%2E+In+Proceedings+of+the+SIAM+Computational+Information+Retrieval+Workshop%2C+pages+157%E2%80%93169%2C+Raleigh%2C+NC%2E)
5. Mark Changizi. 2008. Economically organized hierarchies in WordNet and the Oxford English Dictionary. Cognitive Systems Research, 9(3):214–228. [find](https://scholar.google.com/scholar?q=Mark+Changizi%2E+2008%2E+Economically+organized+hierarchies+in+WordNet+and+the+Oxford+English+Dictionary%2E+Cognitive+Systems+Research%2C+9%283%29%3A214%E2%80%93228%2E)
6. Kenneth Church and Patrick Hanks. 1989. Word association norms, mutual information, and lexicography. In Proceedings of the 27th Annual Conference of the Association of Computational Linguistics, pages 76–83, Vancouver, British Columbia. [find](https://scholar.google.com/scholar?q=Kenneth+Church+and+Patrick+Hanks%2E+1989%2E+Word+association+norms%2C+mutual+information%2C+and+lexicography%2E+In+Proceedings+of+the+27th+Annual+Conference+of+the+Association+of+Computational+Linguistics%2C+page) [our card](https://md.research.elamur.ai/free/en/papers/church-1990-word-association-norms-mutual-information/)
7. Max Coltheart. 1981. The MRC psycholinguistic database. Quarterly Journal of Experimental Psychology, 33A(4):497–505. [find](https://scholar.google.com/scholar?q=Max+Coltheart%2E+1981%2E+The+MRC+psycholinguistic+database%2E+Quarterly+Journal+of+Experimental+Psychology%2C+33A%284%29%3A497%E2%80%93505%2E)
8. Marcel Danesi. 2003. Metaphorical “networks” and verbal communication: A semiotic perspective on human discourse. Sign Systems Studies, 31:341–363. [find](https://scholar.google.com/scholar?q=Marcel+Danesi%2E+2003%2E+Metaphorical+%E2%80%9Cnetworks%E2%80%9D+and+verbal+communication%3A+A+semiotic+perspective+on+human+discourse%2E+Sign+Systems+Studies%2C+31%3A341%E2%80%93363%2E)
9. Mark Davies. 2009. The 385+ million word Corpus of Contemporary American English (1990–2008+): Design, architecture, and linguistic insights. International Journal of Corpus Linguistics, 14(2):159–190. [find](https://scholar.google.com/scholar?q=Mark+Davies%2E+2009%2E+The+385%2B+million+word+Corpus+of+Contemporary+American+English+%281990%E2%80%932008%2B%29%3A+Design%2C+architecture%2C+and+linguistic+insights%2E+International+Journal+of+Corpus+Linguistics%2C+14%282%29%3A159%E2%80%93190)
10. Koen Deschacht and Marie-Francine Moens. 2007. Text analysis for automatic image annotation. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 1000–1007. [find](https://scholar.google.com/scholar?q=Koen+Deschacht+and+Marie%2DFrancine+Moens%2E+2007%2E+Text+analysis+for+automatic+image+annotation%2E+In+Proceedings+of+the+45th+Annual+Meeting+of+the+Association+of+Computational+Linguistics%2C+pages+1000%E2%80%931007%2E)
11. William B. Dolan. 1995. Metaphor as an emergent property of machine-readable dictionaries. In Proceedings of the AAAI 1995 Spring Symposium Series: Representation and Acquisition of Lexical Knowledge: Polysemy, Ambiguity and Generativity, pages 27–32. [find](https://scholar.google.com/scholar?q=William+B%2E+Dolan%2E+1995%2E+Metaphor+as+an+emergent+property+of+machine%2Dreadable+dictionaries%2E+In+Proceedings+of+the+AAAI+1995+Spring+Symposium+Series%3A+Representation+and+Acquisition+of+Lexical+Knowledge%3A)
12. Dedre Gentner, Brian F. Bowdle, Phillip Wolff, and Consuelo Boronat. 2001. Metaphor is like analogy. In D. Gentner, K. J. Holyoak, and B. N. Kokinov, editors, The analogical mind: Perspectives from Cognitive Science, pages 199–253. MIT Press, Cambridge, MA. [find](https://scholar.google.com/scholar?q=Dedre+Gentner%2C+Brian+F%2E+Bowdle%2C+Phillip+Wolff%2C+and+Consuelo+Boronat%2E+2001%2E+Metaphor+is+like+analogy%2E+In+D%2E+Gentner%2C+K%2E+J%2E+Holyoak%2C+and+B%2E+N%2E+Kokinov%2C+editors%2C+The+analogical+mind%3A+Perspectives+from+Co)
13. Chikara Hashimoto and Daisuke Kawahara. 2009. Compilation of an idiom example database for supervised idiom identification. Language Resources and Evaluation, 43(4):355–384. [find](https://scholar.google.com/scholar?q=Chikara+Hashimoto+and+Daisuke+Kawahara%2E+2009%2E+Compilation+of+an+idiom+example+database+for+supervised+idiom+identification%2E+Language+Resources+and+Evaluation%2C+43%284%29%3A355%E2%80%93384%2E)
14. George Lakoff and Mark Johnson. 1980. Metaphors We Live By. University Of Chicago Press, Chicago, IL. [find](https://scholar.google.com/scholar?q=George+Lakoff+and+Mark+Johnson%2E+1980%2E+Metaphors+We+Live+By%2E+University+Of+Chicago+Press%2C+Chicago%2C+IL%2E)
15. Thomas K. Landauer and Susan T. Dumais. 1997. A solution to Plato’s problem: The latent semantic analysis theory of the acquisition, induction, and representation of knowledge. Psychological Review, 104(2):211– 240. [find](https://scholar.google.com/scholar?q=Thomas+K%2E+Landauer+and+Susan+T%2E+Dumais%2E+1997%2E+A+solution+to+Plato%E2%80%99s+problem%3A+The+latent+semantic+analysis+theory+of+the+acquisition%2C+induction%2C+and+representation+of+knowledge%2E+Psychological+Review%2C+1)
16. Saskia Le Cessie and J.C. Van Houwelingen. 1992. Ridge estimators in logistic regression. Applied Statistics, 41(1):191–201. [find](https://scholar.google.com/scholar?q=Saskia+Le+Cessie+and+J%2EC%2E+Van+Houwelingen%2E+1992%2E+Ridge+estimators+in+logistic+regression%2E+Applied+Statistics%2C+41%281%29%3A191%E2%80%93201%2E)
17. Alexis Madrigal. 2011. Why are spy researchers building a ‘Metaphor Program’? The Atlantic, May 25. [find](https://scholar.google.com/scholar?q=Alexis+Madrigal%2E+2011%2E+Why+are+spy+researchers+building+a+%E2%80%98Metaphor+Program%E2%80%99%3F+The+Atlantic%2C+May+25%2E)
18. James H. Martin. 1992. Computer understanding of conventional metaphoric language. Cognitive Science, 16(2):233–270. [find](https://scholar.google.com/scholar?q=James+H%2E+Martin%2E+1992%2E+Computer+understanding+of+conventional+metaphoric+language%2E+Cognitive+Science%2C+16%282%29%3A233%E2%80%93270%2E)
19. Zachary Mason. 2004. CorMet: A computational, corpus-based conventional metaphor extraction system. Computational Linguistics, 30(1):23–44. [find](https://scholar.google.com/scholar?q=Zachary+Mason%2E+2004%2E+CorMet%3A+A+computational%2C+corpus%2Dbased+conventional+metaphor+extraction+system%2E+Computational+Linguistics%2C+30%281%29%3A23%E2%80%9344%2E)
20. Guido Minnen, John Carroll, and Darren Pearce. 2001. Applied morphological processing of English. Natural Language Engineering, 7(3):207–223. [find](https://scholar.google.com/scholar?q=Guido+Minnen%2C+John+Carroll%2C+and+Darren+Pearce%2E+2001%2E+Applied+morphological+processing+of+English%2E+Natural+Language+Engineering%2C+7%283%29%3A207%E2%80%93223%2E)
21. Roberto Navigli. 2009. Word sense disambiguation: A survey. ACM Computing Surveys, 41(2):1–69. [find](https://scholar.google.com/scholar?q=Roberto+Navigli%2E+2009%2E+Word+sense+disambiguation%3A+A+survey%2E+ACM+Computing+Surveys%2C+41%282%29%3A1%E2%80%9369%2E)
22. Yair Neuman and Ophir Nave. 2009. Metaphor-based meaning excavation. Information Sciences, 179:2719– 2728. [find](https://scholar.google.com/scholar?q=Yair+Neuman+and+Ophir+Nave%2E+2009%2E+Metaphor%2Dbased+meaning+excavation%2E+Information+Sciences%2C+179%3A2719%E2%80%93+2728%2E)
23. Malvina Nissim and Katja Markert. 2003. Syntactic features and word similarity for supervised metonymy resolution. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL-03), pages 56–63, Sapporo, Japan. [find](https://scholar.google.com/scholar?q=Malvina+Nissim+and+Katja+Markert%2E+2003%2E+Syntactic+features+and+word+similarity+for+supervised+metonymy+resolution%2E+In+Proceedings+of+the+41st+Annual+Meeting+of+the+Association+for+Computational+Lingui)
24. Reinhard Rapp. 2003. Word sense discovery based on sense descriptor dissimilarity. In Proceedings of the Ninth Machine Translation Summit, pages 315–322. [find](https://scholar.google.com/scholar?q=Reinhard+Rapp%2E+2003%2E+Word+sense+discovery+based+on+sense+descriptor+dissimilarity%2E+In+Proceedings+of+the+Ninth+Machine+Translation+Summit%2C+pages+315%E2%80%93322%2E)
25. Gerard Salton, Anita Wong, and Chung-Shu Yang. 1975. A vector space model for automatic indexing. Communications of the ACM, 18(11):613–620. [find](https://scholar.google.com/scholar?q=Gerard+Salton%2C+Anita+Wong%2C+and+Chung%2DShu+Yang%2E+1975%2E+A+vector+space+model+for+automatic+indexing%2E+Communications+of+the+ACM%2C+18%2811%29%3A613%E2%80%93620%2E)
26. Peter D. Turney and Michael L. Littman. 2003. Measuring praise and criticism: Inference of semantic orientation from association. ACM Transactions on Information Systems, 21(4):315–346. [find](https://scholar.google.com/scholar?q=Peter+D%2E+Turney+and+Michael+L%2E+Littman%2E+2003%2E+Measuring+praise+and+criticism%3A+Inference+of+semantic+orientation+from+association%2E+ACM+Transactions+on+Information+Systems%2C+21%284%29%3A315%E2%80%93346%2E)
27. Peter D. Turney and Patrick Pantel. 2010. From frequency to meaning: Vector space models of semantics. Journal of Artificial Intelligence Research, 37:141– 188. [find](https://scholar.google.com/scholar?q=Peter+D%2E+Turney+and+Patrick+Pantel%2E+2010%2E+From+frequency+to+meaning%3A+Vector+space+models+of+semantics%2E+Journal+of+Artificial+Intelligence+Research%2C+37%3A141%E2%80%93+188%2E)
28. Ian H. Witten and Eibe Frank. 2005. Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann, San Francisco. [find](https://scholar.google.com/scholar?q=Ian+H%2E+Witten+and+Eibe+Frank%2E+2005%2E+Data+Mining%3A+Practical+Machine+Learning+Tools+and+Techniques+with+Java+Implementations%2E+Morgan+Kaufmann%2C+San+Francisco%2E)
29. Xing Xing, Yi Zhang, and Mei Han. 2010. Query difficulty prediction for contextual image retrieval. In Advances in Information Retrieval, volume 5993 of Lecture Notes in Computer Science, pages 581–585. Springer. [find](https://scholar.google.com/scholar?q=Xing+Xing%2C+Yi+Zhang%2C+and+Mei+Han%2E+2010%2E+Query+difficulty+prediction+for+contextual+image+retrieval%2E+In+Advances+in+Information+Retrieval%2C+volume+5993+of+Lecture+Notes+in+Computer+Science%2C+pages+581%E2%80%9358)