---
title: "Neural Metaphor Detection in Context — Gao 2018"
description: "Both models share a simple design. 72.6 F1. 32 references, cited by 72 papers here."
authors: ["Ge Gao", "Eunsol Choi", "Yejin Choi", "Luke Zettlemoyer"]
year: 2018
venue: "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D18-1060/"
doi: "10.18653/v1/d18-1060"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/gao-2018-neural-metaphor-detection-context/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/gao-2018-neural-metaphor-detection-context/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/3/) / Neural Metaphor Detection in Context

# Neural Metaphor Detection in Context

**Authors:** Ge Gao, [Eunsol Choi](https://md.research.elamur.ai/free/en/authors/eunsol-choi/), [Yejin Choi](https://md.research.elamur.ai/free/en/authors/yejin-choi/) and [Luke Zettlemoyer](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/) · **Year:** 2018 · **Venue:** Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/D18-1060/) · [PDF](https://aclanthology.org/D18-1060.pdf) · [DOI 10.18653/v1/d18-1060](https://doi.org/10.18653/v1/d18-1060) · [OpenAlex](https://openalex.org/W2963272610)

**Citations:** 126 citations (OpenAlex, 2026-10-14) · [72](https://md.research.elamur.ai/free/en/papers/gao-2018-neural-metaphor-detection-context/cited-by/) in our library, of the 140,884 papers whose bibliographies we read

## Summary
The paper addresses metaphor detection: deciding whether a word in a sentence is used figuratively. Earlier systems often reduced context to subject–verb–object triples or relied on shallow unigram features. The authors show that the full sentence gives the model more useful evidence. They test two setups: tagging every word in a sentence for metaphoricity (sequence labeling) and judging a single target verb (classification). Both models share a simple design. Each token is represented by GloVe embeddings concatenated with contextual ELMo vectors and fed to a BiLSTM. The classification variant adds a target-position embedding and attention pooling. Evaluation covers VUA, TroFi and MOH-X. The models set new state-of-the-art results on VUA and MOH-X. Removing ELMo causes large drops, which shows how much contextual embeddings help. When every word in a sentence is annotated, the tagging model is better than the classifier even for judging verbs. The work matters because it sets a strong and easily reproducible neural baseline for figurative-language processing, and the code is public.

## Key points
- On VUA sequence labeling, the SEQ model reaches 72.6 F1, compared with 65.1 for the Wu et al. (2018) ensemble (+7.5). It mainly gains recall over a frequency-based lexical baseline.
- On verb classification, the paper reports these results:
  - VUA: SEQ reaches 69.7 F1, +2.5 over the previous best.
  - MOH-X: CLS reaches 79.1 F1, +4.9 over Rei et al. (2017).
  - TroFi: Köper and im Walde (2017) still lead with 75.0 F1, versus about 72 for the authors' models.
- The verb datasets differ in size: 647 examples (MOH-X), 3,737 (TroFi) and 23,113 (VUA, with over 2K unique verbs). TroFi covers only 50 distinct verbs.
- In the ablation on the VUA dev set, removing ELMo lowers F1 from 70.4 to 61.7 for SEQ and from 57.3 to 50.8 for CLS.
- The error analysis of 100 dev mistakes found that many are borderline cases, which reflects how subjective the annotation is. The code is published at github.com/gao-g/metaphor-in-context.

*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: [🧷 Idioms & multiword expressions](https://md.research.elamur.ai/free/en/topics/multiword-expressions/)

## Institutions

- [University of Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) — University, Seattle, United States · 206 works · 158,423 citations
- [Allen Institute for Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/allen-institute-for-artificial-intelligence/) — Research institute, Seattle, United States · 169 works · 65,355 citations

## Cite

Cite as: Ge Gao, Eunsol Choi, Yejin Choi and Luke Zettlemoyer. 2018. Neural Metaphor Detection in Context. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.

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

```bibtex
@inproceedings{gao2018neural,
  title = {{Neural Metaphor Detection in Context}},
  author = {Ge Gao, Eunsol Choi, Yejin Choi and Luke Zettlemoyer},
  booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
  year = {2018},
  doi = {10.18653/v1/d18-1060},
  url = {https://doi.org/10.18653/v1/d18-1060}
}
```

- [← previous End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification](https://md.research.elamur.ai/free/en/papers/libovicky-2018-end-end-non-autoregressive-neural/)
- [next → Retrieval of the Best Counterargument without Prior Topic Knowledge](https://md.research.elamur.ai/free/en/papers/wachsmuth-2018-retrieval-best-counterargument-without-prior/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/3/)

## References

32 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. George Lakoff and Mark Johnson. 1980. Metaphors we live by. The University of Chicago Press. [find](https://scholar.google.com/scholar?q=George+Lakoff+and+Mark+Johnson%2E+1980%2E+Metaphors+we+live+by%2E+The+University+of+Chicago+Press%2E)
2. Julia Birke and Anoop Sarkar. 2006. A clustering approach for nearly unsupervised recognition of non-literal language. In EACL. [find](https://scholar.google.com/scholar?q=Julia+Birke+and+Anoop+Sarkar%2E+2006%2E+A+clustering+approach+for+nearly+unsupervised+recognition+of+non%2Dliteral+language%2E+In+EACL%2E)
3. Saif Mohammad, Ekaterina Shutova, and Peter D. Turney. 2016. Metaphor as a medium for emotion: An empirical study. In Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics (*Sem). [our card](https://md.research.elamur.ai/free/en/papers/mohammad-2016-metaphor-as-medium-emotion-empirical/)
4. Yuri Bizzoni and Mehdi Ghanimifard. 2018. Bigrams and bilstms two neural networks for sequential metaphor detection. In Proceedings of the Workshop on Figurative Language Processing, NAACL, pages 91–101. [find](https://scholar.google.com/scholar?q=Yuri+Bizzoni+and+Mehdi+Ghanimifard%2E+2018%2E+Bigrams+and+bilstms+two+neural+networks+for+sequential+metaphor+detection%2E+In+Proceedings+of+the+Workshop+on+Figurative+Language+Processing%2C+NAACL%2C+pages+91%E2%80%931)
5. Anna Mosolova, Ivan Bondarenko, and Vadim Fomin. 2018. Conditional random fields for metaphor detection. In Proceedings of the Workshop on Figurative Language Processing, NAACL, pages 121–123. [find](https://scholar.google.com/scholar?q=Anna+Mosolova%2C+Ivan+Bondarenko%2C+and+Vadim+Fomin%2E+2018%2E+Conditional+random+fields+for+metaphor+detection%2E+In+Proceedings+of+the+Workshop+on+Figurative+Language+Processing%2C+NAACL%2C+pages+121%E2%80%93123%2E)
6. George Aaron Broadwell, Umit Boz, Ignacio Cases, Tomek Strzalkowski, Laurie Feldman, Sarah M. Taylor, Samira Shaikh, Ting Liu, Kit Cho, and Nick Webb. 2013. Using imageability and topic chaining to locate metaphors in linguistic corpora. In SBP. [find](https://scholar.google.com/scholar?q=George+Aaron+Broadwell%2C+Umit+Boz%2C+Ignacio+Cases%2C+Tomek+Strzalkowski%2C+Laurie+Feldman%2C+Sarah+M%2E+Taylor%2C+Samira+Shaikh%2C+Ting+Liu%2C+Kit+Cho%2C+and+Nick+Webb%2E+2013%2E+Using+imageability+and+topic+chaining+to+lo)
7. Agnieszka Mykowiecka, Aleksander Wawer, and Magorzata Aneta Marciniak. 2018. Detecting figurative word occurrences using recurrent neural networks. In Proceedings of the Workshop on Figurative Language Processing, NAACL, pages 124–127. [find](https://scholar.google.com/scholar?q=Agnieszka+Mykowiecka%2C+Aleksander+Wawer%2C+and+Magorzata+Aneta+Marciniak%2E+2018%2E+Detecting+figurative+word+occurrences+using+recurrent+neural+networks%2E+In+Proceedings+of+the+Workshop+on+Figurative+Languag)
8. Luana Bulat, Stephen Clark, and Ekaterina Shutova. 2017. Modelling metaphor with attribute-based semantics. In EACL. [find](https://scholar.google.com/scholar?q=Luana+Bulat%2C+Stephen+Clark%2C+and+Ekaterina+Shutova%2E+2017%2E+Modelling+metaphor+with+attribute%2Dbased+semantics%2E+In+EACL%2E)
9. Gözde Özbal, Carlo Strapparava, Serra Sinem Tekiroglu, and Daniele Pighin. 2016. Learning to identify metaphors from a corpus of proverbs. In EMNLP. [find](https://scholar.google.com/scholar?q=Go%CC%88zde+O%CC%88zbal%2C+Carlo+Strapparava%2C+Serra+Sinem+Tekiroglu%2C+and+Daniele+Pighin%2E+2016%2E+Learning+to+identify+metaphors+from+a+corpus+of+proverbs%2E+In+EMNLP%2E)
10. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. 9(8):1735–1780. [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter+and+Ju%CC%88rgen+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+9%288%29%3A1735%E2%80%931780%2E)
11. Matthew Honnibal and Ines Montani. 2017. spacy 2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. [find](https://scholar.google.com/scholar?q=Matthew+Honnibal+and+Ines+Montani%2E+2017%2E+spacy+2%3A+Natural+language+understanding+with+bloom+embeddings%2C+convolutional+neural+networks+and+incremental+parsing%2E)
12. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global vectors for word representation. In EMNLP, pages 1532–1543. [our card](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/)
13. Dirk Hovy, Shashank Shrivastava, Sujay Kumar Jauhar, Mrinmaya Sachan, Kartik Goyal, Huying Li, Whitney Sanders, and Eduard H. Hovy. 2013. Identifying metaphorical word use with tree kernels. In Proceedings of the First Workshop on Metaphor in NLP, ACL, pages 52–57. [find](https://scholar.google.com/scholar?q=Dirk+Hovy%2C+Shashank+Shrivastava%2C+Sujay+Kumar+Jauhar%2C+Mrinmaya+Sachan%2C+Kartik+Goyal%2C+Huying+Li%2C+Whitney+Sanders%2C+and+Eduard+H%2E+Hovy%2E+2013%2E+Identifying+metaphorical+word+use+with+tree+kernels%2E+In+Procee)
14. Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matthew Gardner, Christopher Clark, Kenton Lee, and Luke S. Zettlemoyer. 2018. Deep contextualized word representations. abs/1802.05365. [our card](https://md.research.elamur.ai/free/en/papers/peters-2018-deep-contextualized-word-representations/)
15. Malay Pramanick, Ashim Gupta, and Pabitra Mitra. 2018. An lstm-crf based approach to token-level metaphor detection. In Proceedings of the Workshop on Figurative Language Processing, NAACL, pages 67–75. [find](https://scholar.google.com/scholar?q=Malay+Pramanick%2C+Ashim+Gupta%2C+and+Pabitra+Mitra%2E+2018%2E+An+lstm%2Dcrf+based+approach+to+token%2Dlevel+metaphor+detection%2E+In+Proceedings+of+the+Workshop+on+Figurative+Language+Processing%2C+NAACL%2C+pages+67%E2%80%937)
16. Hyeju Jang, Yohan Jo, Qinlan Shen, Michael Miller, Seungwhan Moon, and Carolyn Penstein Rosé. 2016. Metaphor detection with topic transition, emotion and cognition in context. In ACL. [find](https://scholar.google.com/scholar?q=Hyeju+Jang%2C+Yohan+Jo%2C+Qinlan+Shen%2C+Michael+Miller%2C+Seungwhan+Moon%2C+and+Carolyn+Penstein+Rose%CC%81%2E+2016%2E+Metaphor+detection+with+topic+transition%2C+emotion+and+cognition+in+context%2E+In+ACL%2E)
17. Marek Rei, Luana Bulat, Douwe Kiela, and Ekaterina Shutova. 2017. Grasping the finer point: A supervised similarity network for metaphor detection. In EMNLP. [find](https://scholar.google.com/scholar?q=Marek+Rei%2C+Luana+Bulat%2C+Douwe+Kiela%2C+and+Ekaterina+Shutova%2E+2017%2E+Grasping+the+finer+point%3A+A+supervised+similarity+network+for+metaphor+detection%2E+In+EMNLP%2E)
18. Diederik P Kingma and Jimmy Ba. 2013. Adam: A method for stochastic optimization. [find](https://scholar.google.com/scholar?q=Diederik+P+Kingma+and+Jimmy+Ba%2E+2013%2E+Adam%3A+A+method+for+stochastic+optimization%2E)
19. Beata Beigman Klebanov, Chee Wee Leong, E. Dario Gutiérrez, Ekaterina Shutova, and Michael Flor. 2016. Semantic classifications for detection of verb metaphors. In ACL. [find](https://scholar.google.com/scholar?q=Beata+Beigman+Klebanov%2C+Chee+Wee+Leong%2C+E%2E+Dario+Gutie%CC%81rrez%2C+Ekaterina+Shutova%2C+and+Michael+Flor%2E+2016%2E+Semantic+classifications+for+detection+of+verb+metaphors%2E+In+ACL%2E)
20. Ekaterina Shutova, Douwe Kiela, and Jean Maillard. 2016. Black holes and white rabbits: Metaphor identification with visual features. In HLT-NAACL. [our card](https://md.research.elamur.ai/free/en/papers/shutova-2016-black-holes-white-rabbits-metaphor/)
21. Beata Beigman Klebanov, Chee Wee Leong, Michael Heilman, and Michael Flor. 2014. Different texts, same metaphors: Unigrams and beyond. In Proceedings of the Second Workshop on Metaphor in NLP, ACL. [find](https://scholar.google.com/scholar?q=Beata+Beigman+Klebanov%2C+Chee+Wee+Leong%2C+Michael+Heilman%2C+and+Michael+Flor%2E+2014%2E+Different+texts%2C+same+metaphors%3A+Unigrams+and+beyond%2E+In+Proceedings+of+the+Second+Workshop+on+Metaphor+in+NLP%2C+ACL%2E)
22. Gerard J Steen, Aletta G Dorst, J Berenike Herrmann, Anna A Kaal, and Tina Krennmayr. 2010. Metaphor in usage. 21(4):765796. [find](https://scholar.google.com/scholar?q=Gerard+J+Steen%2C+Aletta+G+Dorst%2C+J+Berenike+Herrmann%2C+Anna+A+Kaal%2C+and+Tina+Krennmayr%2E+2010%2E+Metaphor+in+usage%2E+21%284%29%3A765796%2E)
23. Maximilian Köper and Sabine Schulte im Walde. 2016. Distinguishing literal and non-literal usage of german particle verbs. In HLT-NAACL. [find](https://scholar.google.com/scholar?q=Maximilian+Ko%CC%88per+and+Sabine+Schulte+im+Walde%2E+2016%2E+Distinguishing+literal+and+non%2Dliteral+usage+of+german+particle+verbs%2E+In+HLT%2DNAACL%2E)
24. Egon W. Stemle and Alexander Onysko. 2018. Using language learner data for metaphor detection. In Proceedings of the Workshop on Figurative Language Processing, NAACL, pages 133–138. [find](https://scholar.google.com/scholar?q=Egon+W%2E+Stemle+and+Alexander+Onysko%2E+2018%2E+Using+language+learner+data+for+metaphor+detection%2E+In+Proceedings+of+the+Workshop+on+Figurative+Language+Processing%2C+NAACL%2C+pages+133%E2%80%93138%2E)
25. Maximilian Köper and Sabine Schulte im Walde. 2017. Improving verb metaphor detection by propagating abstractness to words, phrases and individual senses. In Proceedings of the First Workshop on Sense, Concept and Entity Representations and their Applications, pages 24–30. [find](https://scholar.google.com/scholar?q=Maximilian+Ko%CC%88per+and+Sabine+Schulte+im+Walde%2E+2017%2E+Improving+verb+metaphor+detection+by+propagating+abstractness+to+words%2C+phrases+and+individual+senses%2E+In+Proceedings+of+the+First+Workshop+on+Sens)
26. Tomek Strzalkowski, George Aaron Broadwell, Sarah Taylor, Laurie Feldman, Samira Shaikh, Ting Liu, Boris Yamrom, Kit Cho, Umit Boz, Ignacio Cases, and Kyle Elliot. 2013. Robust extraction of metaphor from novel data. In Proceedings of the First Workshop on Metaphor in NLP, ACL. [find](https://scholar.google.com/scholar?q=Tomek+Strzalkowski%2C+George+Aaron+Broadwell%2C+Sarah+Taylor%2C+Laurie+Feldman%2C+Samira+Shaikh%2C+Ting+Liu%2C+Boris+Yamrom%2C+Kit+Cho%2C+Umit+Boz%2C+Ignacio+Cases%2C+and+Kyle+Elliot%2E+2013%2E+Robust+extraction+of+metaphor+)
27. Krishnkant Swarnkar and Anil Kumar Singh. 2018. Di-lstm contrast : A deep neural network for metaphor detection. In Proceedings of the Workshop on Figurative Language Processing, NAACL, pages 115–120. [find](https://scholar.google.com/scholar?q=Krishnkant+Swarnkar+and+Anil+Kumar+Singh%2E+2018%2E+Di%2Dlstm+contrast+%3A+A+deep+neural+network+for+metaphor+detection%2E+In+Proceedings+of+the+Workshop+on+Figurative+Language+Processing%2C+NAACL%2C+pages+115%E2%80%93120%2E)
28. Serra Sinem Tekiroglu, Gözde Özbal, and Carlo Strapparava. 2015. Exploring sensorial features for metaphor identification. In Proceedings of the Third Workshop on Metaphor in NLP, ACL. [find](https://scholar.google.com/scholar?q=Serra+Sinem+Tekiroglu%2C+Go%CC%88zde+O%CC%88zbal%2C+and+Carlo+Strapparava%2E+2015%2E+Exploring+sensorial+features+for+metaphor+identification%2E+In+Proceedings+of+the+Third+Workshop+on+Metaphor+in+NLP%2C+ACL%2E)
29. Yulia Tsvetkov, Leonid Boytsov, Anatole Gershman, Eric Nyberg, and Chris Dyer. 2014. Metaphor detection with cross-lingual model transfer. In ACL. [our card](https://md.research.elamur.ai/free/en/papers/tsvetkov-2014-metaphor-detection-cross-lingual-model/)
30. Yulia Tsvetkov, Elena Mukomel, and Anatole Gershman. 2013. Cross-lingual metaphor detection using common semantic features. In Proceedings of the First Workshop on Metaphor in NLP, ACL. [find](https://scholar.google.com/scholar?q=Yulia+Tsvetkov%2C+Elena+Mukomel%2C+and+Anatole+Gershman%2E+2013%2E+Cross%2Dlingual+metaphor+detection+using+common+semantic+features%2E+In+Proceedings+of+the+First+Workshop+on+Metaphor+in+NLP%2C+ACL%2E)
31. Peter D. Turney, Yair Neuman, Dan Assaf, and Yohai Cohen. 2011. Literal and metaphorical sense identification through concrete and abstract context. In EMNLP. [our card](https://md.research.elamur.ai/free/en/papers/turney-2011-literal-metaphorical-sense-identification-through/)
32. Chuhan Wu, Fangzhao Wu, Yubo Chen, Sixing Wu, Zhigang Yuan, and Yongfeng Huang. 2018. Neural metaphor detecting with cnn-lstm model. In Proceedings of the Workshop on Figurative Language Processing, NAACL, pages 110–114. [find](https://scholar.google.com/scholar?q=Chuhan+Wu%2C+Fangzhao+Wu%2C+Yubo+Chen%2C+Sixing+Wu%2C+Zhigang+Yuan%2C+and+Yongfeng+Huang%2E+2018%2E+Neural+metaphor+detecting+with+cnn%2Dlstm+model%2E+In+Proceedings+of+the+Workshop+on+Figurative+Language+Processing%2C+N)