---
title: "Contextualized Sensorimotor Norms — paper by Trott and Bergen (2022)"
description: "Trott and Bergen build the Contextualized Sensorimotor Norms (CS Norms), in which people rate how strongly a target… 57 references, cited by 2 papers here."
authors: ["Sean Trott", "Benjamin Bergen"]
year: 2022
venue: "arXiv:2203.05648"
source: "https://arxiv.org/abs/2203.05648"
doi: "10.48550/arxiv.2203.05648"
arxiv: "2203.05648"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/trott-2022-contextualized-sensorimotor-norms-multi-dimensional/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/trott-2022-contextualized-sensorimotor-norms-multi-dimensional/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2022](https://md.research.elamur.ai/free/en/papers/2022/page/6/) / Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context

# Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context

**Authors:** Sean Trott and [Benjamin Bergen](https://md.research.elamur.ai/free/en/authors/benjamin-bergen/) · **Year:** 2022 · **Venue:** arXiv:2203.05648 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2203.05648) · [PDF](https://arxiv.org/pdf/2203.05648) · [DOI 10.48550/arxiv.2203.05648](https://doi.org/10.48550/arxiv.2203.05648) · [arXiv 2203.05648](https://arxiv.org/abs/2203.05648)

**Citations:** 2 in our library, of the 141,840 papers whose bibliographies we read

## Summary
Sensorimotor resources such as the Lancaster Sensorimotor Norms assign each word one profile, rated without context. Yet most English words are ambiguous or polysemous, and a "data table" and a "wooden table" engage the senses very differently. Trott and Bergen build the Contextualized Sensorimotor Norms (CS Norms), in which people rate how strongly a target word, as used in a specific sentence, is experienced through six perceptual modalities and five bodily action effectors. The sentences come from RAW-C: 112 ambiguous words, each placed in four controlled contexts, with relatedness and sense-dominance judgments already attached. Native-speaker undergraduates followed the Lancaster protocol and supplied at least ten ratings per sentence for each judgment type.

The contextual ratings partly overlap with the isolated-word norms but carry distinct information. They also track sense boundaries and meaning dominance. A sensorimotor distance between two uses of a word predicts human relatedness judgments better than BERT-derived measures alone. The authors propose the resource as a test bed for grounded language models.

## Key points
- The resource covers 112 English words in 4 sentences each, 448 sentences in total, all taken from RAW-C (672 sentence pairs with relatedness and dominance ratings).
- Two judgment types were used, both on a 0–5 scale:
  - Perception: Vision, Hearing, Touch, Interoception, Smell, Taste.
  - Action: Hand/Arm, Foot/Leg, Mouth/Throat, Head, Torso.
- Annotators were filtered as follows:
  - 377 participants were recruited and 283 kept (132 Perception, 151 Action).
  - Exclusions removed non-native speakers, bot-check failures, and anyone whose agreement score fell more than 2 SD below the mean.
  - Each person rated about 60 sentences and never saw the same target word twice.
- Data were collected in two stages. The second stage deliberately mixed under-rated and well-rated sentences to fill gaps faster. Agreement distributions showed no behavioral difference between the stages.
- The main results:
  - The CS Norms add variance beyond the ~40,000-word, 11-dimension LS Norms.
  - Dominant meanings tend to be more sensorimotor.
  - Sensorimotor distance correlates with crossing a sense boundary.
  - The same distance improves relatedness prediction over BERT.

## Interesting ideas
- Collect perceptual and motor features per usage in context rather than per lemma, since a single word-level profile blurs incompatible senses together.
- Convert two usages' feature profiles into a numeric distance and read a large distance as evidence that the word has switched sense.
- Judge an interpretable feature by whether it adds predictive power on top of a strong neural baseline, not by its standalone score.
- Filter annotators by agreement with the rest of the pool, and when the collection protocol changes, compare agreement distributions to confirm behavior stayed stable.
- Use a small, hand-controlled set of one word in several contexts as a challenge set rather than as training data.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (world): Attach sensorimotor and perceptual properties to WordNet senses or to individual entity instances in the text world, so "wooden table" and "data table" receive different property profiles.
- **I2** (frames): During coreference and sense selection, a sharp mismatch in sensorimotor profile between two mentions of the same lemma could lower the score for linking them as one entity.
- **I3** (learn): Evaluate each explainable feature (frame roles, ontology properties) by its incremental gain over a gparse-embedding-only baseline, so only features that contribute something new are kept.
- **I4** (learn): Drop a witness parser whose agreement with the silver consensus is an outlier, and compare agreement distributions before and after any pipeline change to catch hidden shifts.
- **I5** (answer): Build a compact test where the same ambiguous word appears in contrasting sentences, to check that readers pick the right sense before answering questions.

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

📚 Shelves (2): [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (1): [English](https://md.research.elamur.ai/free/en/topics/english/) · 1,373 works

## Cite

Cite as: Sean Trott and Benjamin Bergen. 2022. Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context. arXiv:2203.05648.

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

```bibtex
@misc{trott2022contextualized,
  title = {{Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context}},
  author = {Sean Trott and Benjamin Bergen},
  year = {2022},
  doi = {10.48550/arxiv.2203.05648},
  eprint = {2203.05648},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2203.05648}
}
```

- [← previous connotation_clashers at SemEval-2022 Task 6: The effect of sentiment analysis on sarcasm detection](https://md.research.elamur.ai/free/en/papers/hantsch-2022-connotation-clashers-semeval-2022-task/)
- [next → CSECU-DSG @ Causal News Corpus 2022: Fusion of RoBERTa Transformers Variants for Causal Event Classification](https://md.research.elamur.ai/free/en/papers/aziz-2022-csecu-dsg-causal-news-corpus/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/page/6/)

## References

57 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mark Andrews, Stefan Frank, and Gabriella Vigliocco. 2014. Reconciling embodied and distributional accounts of meaning in language. Topics in cognitive science, 6(3):359–370. [↗](https://doi.org/10.1111/tops.12096)
2. Lawrence W. Barsalou. 1999. Perceptual symbol systems. Behavioral and Brain Sciences, 22(4):577– 660. Publisher: Cambridge University Press. [↗](https://doi.org/10.1017/s0140525x99002149)
3. Lawrence W. Barsalou. 2008. Grounded Cognition. Annual Review of Psychology, 59(1):617–645. _eprint: https://doi.org/10.1146/annurev.psych.59.103006.093639. [↗](https://doi.org/10.1146/annurev.psych.59.103006.093639)
4. Douglas Bates, Martin Mächler, Ben Bolker, and Steve Walker. 2015. Fitting linear mixed-effects models using lme4. Journal of Statistical Software, 67(1):1– 48. [↗](https://doi.org/10.18637/jss.v067.i01) [our card](https://md.research.elamur.ai/free/en/papers/bates-2015-fitting-linear-mixed-effects-models/)
5. Emily M. Bender and Alexander Koller. 2020. Climbing towards NLU: On meaning, form, and understanding in the age of data. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5185–5198, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.acl-main.463) [our card](https://md.research.elamur.ai/free/en/papers/bender-2020-climbing-nlu-meaning-form-understanding/)
6. Benjamin Bergen and Jerome Feldman. 2008. 16 -Embodied Concept Learning. In Paco Calvo and Antoni Gomila, editors, Handbook of Cognitive Science, Perspectives on Cognitive Science, pages 313– 331. Elsevier, San Diego. [find](https://scholar.google.com/scholar?q=Benjamin+Bergen+and+Jerome+Feldman%2E+2008%2E+16+%2DEmbodied+Concept+Learning%2E+In+Paco+Calvo+and+Antoni+Gomila%2C+editors%2C+Handbook+of+Cognitive+Science%2C+Perspectives+on+Cognitive+Science%2C+pages+313%E2%80%93+331%2E+Els)
7. Benjamin K. Bergen. 2012. Louder Than Words: The New Science of How the Mind Makes Meaning. Basic Books, New York, NY, USA. [find](https://scholar.google.com/scholar?q=Benjamin+K%2E+Bergen%2E+2012%2E+Louder+Than+Words%3A+The+New+Science+of+How+the+Mind+Makes+Meaning%2E+Basic+Books%2C+New+York%2C+NY%2C+USA%2E)
8. Jeffrey R Binder, Lisa L Conant, Colin J Humphries, Leonardo Fernandino, Stephen B Simons, Mario Aguilar, and Rutvik H Desai. 2016. Toward a brain-based componential semantic representation. Cognitive neuropsychology, 33(3-4):130–174. [↗](https://doi.org/10.1080/02643294.2016.1147426)
9. Katherine S Binder and Keith Rayner. 1998. Contextual strength does not modulate the subordinate bias effect: Evidence from eye fixations and self-paced reading. Psychonomic Bulletin & Review, 5(2):271– 276. [↗](https://doi.org/10.3758/bf03212950)
10. Yonatan Bisk, Ari Holtzman, Jesse Thomason, Jacob Andreas, Yoshua Bengio, Joyce Chai, Mirella Lapata, Angeliki Lazaridou, Jonathan May, Aleksandr Nisnevich, Nicolas Pinto, and Joseph Turian. 2020. Experience grounds language. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8718–8735, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.emnlp-main.703) [our card](https://md.research.elamur.ai/free/en/papers/bisk-2020-experience-grounds-language/)
11. Anna M Borghi, Laura Barca, Ferdinand Binkofski, Cristiano Castelfranchi, Giovanni Pezzulo, and Luca Tummolini. 2019. Words as social tools: Language, sociality and inner grounding in abstract concepts. Physics of life reviews, 29:120–153. [↗](https://doi.org/10.1016/j.plrev.2018.12.001)
12. Marc Brysbaert, Michaël Stevens, Simon De Deyne, Wouter Voorspoels, and Gert Storms. 2014a. Norms of age of acquisition and concreteness for 30,000 dutch words. Acta psychologica, 150:80–84. [↗](https://doi.org/10.1016/j.actpsy.2014.04.010)
13. Marc Brysbaert, Amy Beth Warriner, and Victor Kuperman. 2014b. Concreteness ratings for 40 thousand generally known english word lemmas. Behavior research methods, 46(3):904–911. [↗](https://doi.org/10.3758/s13428-013-0403-5)
14. Emmanuele Chersoni, Rong Xiang, Qin Lu, and Chu-Ren Huang. 2020. Automatic learning of modality exclusivity norms with crosslingual word embeddings. In Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics, pages 32– 38, Barcelona, Spain (Online). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Emmanuele+Chersoni%2C+Rong+Xiang%2C+Qin+Lu%2C+and+Chu%2DRen+Huang%2E+2020%2E+Automatic+learning+of+modality+exclusivity+norms+with+crosslingual+word+embeddings%2E+In+Proceedings+of+the+Ninth+Joint+Conference+on+Lex)
15. Max Coltheart. 1981. The mrc psycholinguistic database. The Quarterly Journal of Experimental Psychology Section A, 33(4):497–505. [↗](https://doi.org/10.1080/14640748108400805)
16. Bojana Ćoso, Marc Guasch, Pilar Ferré, and José Antonio Hinojosa. 2019. Affective and concreteness norms for 3,022 croatian words. Quarterly Journal of Experimental Psychology, 72(9):2302–2312. [↗](https://doi.org/10.1177/1747021819834226)
17. Charles P Davis and Eiling Yee. 2021. Building semantic memory from embodied and distributional language experience. Wiley Interdisciplinary Reviews: Cognitive Science, 12(5):e1555. [↗](https://doi.org/10.1002/wcs.1555)
18. Joshua R De Leeuw. 2015. jspsych: A javascript library for creating behavioral experiments in a web browser. Behavior research methods, 47(1):1–12. [↗](https://doi.org/10.3758/s13428-014-0458-y)
19. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/n19-1423) [our card](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/)
20. Susan A Duffy, Robin K Morris, and Keith Rayner. 1988. Lexical ambiguity and fixation times in reading. Journal of memory and language, 27(4):429– 446. [↗](https://doi.org/10.1016/0749-596x(88)90066-6)
21. Jeffrey L Elman. 2009. On the meaning of words and dinosaur bones: Lexical knowledge without a lexicon. Cognitive science, 33(4):547–582. [↗](https://doi.org/10.1111/j.1551-6709.2009.01023.x)
22. Katrin Erk, Diana McCarthy, and Nicholas Gaylord. 2013. Measuring word meaning in context. Computational Linguistics, 39(3):511–554. [↗](https://doi.org/10.1162/coli_a_00142) [our card](https://md.research.elamur.ai/free/en/papers/erk-2013-measuring-word-meaning-context/)
23. Kenneth J Gilhooly and Robert H Logie. 1980. Meaning-dependent ratings of imagery, age of acquisition, familiarity, and concreteness for 387 ambiguous words. Behavior Research Methods & Instrumentation, 12(4):428–450. [↗](https://doi.org/10.3758/bf03201694)
24. Arthur M Glenberg and Michael P Kaschak. 2002. Grounding language in action. Psychonomic bulletin & review, 9(3):558–565. [↗](https://doi.org/10.3758/bf03196313)
25. Janosch Haber and Massimo Poesio. 2021. Patterns of polysemy and homonymy in contextualised language models. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2663–2676, Punta Cana, Dominican Republic. Association for Computational Linguistics. [↗](https://doi.org/10.48448/ezpz-zy96)
26. Stevan Harnad. 1990. The symbol grounding problem. Physica D: Nonlinear Phenomena, 42(1):335 – 346. [↗](https://doi.org/10.1016/0167-2789(90)90087-6)
27. Joseph Henrich, Steven J Heine, and Ara Norenzayan. 2010. Most people are not weird. Nature, 466(7302):29–29. [↗](https://doi.org/10.1038/466029a)
28. Brendan T Johns. 2021. Distributional social semantics: Inferring word meanings from communication patterns. Cognitive Psychology, 131:101441. [↗](https://doi.org/10.1016/j.cogpsych.2021.101441)
29. Taelin Karidi, Yichu Zhou, Nathan Schneider, Omri Abend, and Vivek Srikumar. 2021. Putting words in BERT’s mouth: Navigating contextualized vector spaces with pseudowords. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10300–10313, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Taelin+Karidi%2C+Yichu+Zhou%2C+Nathan+Schneider%2C+Omri+Abend%2C+and+Vivek+Srikumar%2E+2021%2E+Putting+words+in+BERT%E2%80%99s+mouth%3A+Navigating+contextualized+vector+spaces+with+pseudowords%2E+In+Proceedings+of+the+2021+C)
30. Casey Kennington. 2021. Enriching language models with visually-grounded word vectors and the Lancaster sensorimotor norms. In Proceedings of the 25th Conference on Computational Natural Language Learning, pages 148–157, Online. Association for Computational Linguistics. [↗](https://doi.org/10.48448/93qk-ze94)
31. Jamie Kiros, William Chan, and Geoffrey Hinton. 2018. Illustrative language understanding: Large-scale visual grounding with image search. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 922–933, Melbourne, Australia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jamie+Kiros%2C+William+Chan%2C+and+Geoffrey+Hinton%2E+2018%2E+Illustrative+language+understanding%3A+Large%2Dscale+visual+grounding+with+image+search%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+)
32. Dermot Lynott, Louise Connell, Marc Brysbaert, James Brand, and James Carney. 2019. The lancaster sensorimotor norms: multidimensional measures of perceptual and action strength for 40,000 english words. Behavior Research Methods, pages 1–21. [↗](https://doi.org/10.3758/s13428-019-01316-z)
33. Asifa Majid. 2020. Human olfaction at the intersection of language, culture, and biology. Trends in Cognitive Sciences. [↗](https://doi.org/10.1016/j.tics.2020.11.005)
34. Aurélie Miceli, Erika Wauthia, Laurent Lefebvre, Laurence Ris, and Isabelle Simoes Loureiro. 2021. Perceptual and interoceptive strength norms for 270 french words. Frontiers in Psychology, 12:2018. [↗](https://doi.org/10.3389/fpsyg.2021.667271)
35. Friedemann Pulvermüller. 1999. Words in the brain’s language. Behavioral and brain sciences, 22(2):253–279. [find](https://scholar.google.com/scholar?q=Friedemann+Pulverm%C3%BCller%2E+1999%2E+Words+in+the+brain%E2%80%99s+language%2E+Behavioral+and+brain+sciences%2C+22%282%29%3A253%E2%80%93279%2E)
36. Keith Rayner, Jeremy M Pacht, and Susan A Duffy. 1994. Effects of prior encounter and global discourse bias on the processing of lexically ambiguous words: Evidence from eye fixations. Journal of memory and language, 33(4):527–544. [↗](https://doi.org/10.1006/jmla.1994.1025)
37. W Gudrun Reijnierse, Christian Burgers, Marianna Bolognesi, and Tina Krennmayr. 2019. How polysemy affects concreteness ratings: the case of metaphor. Cognitive science, 43(8):e12779. [↗](https://doi.org/10.1111/cogs.12779)
38. Jennifer M Rodd, M Gareth Gaskell, and William D Marslen-Wilson. 2004. Modelling the effects of semantic ambiguity in word recognition. Cognitive science, 28(1):89–104. [↗](https://doi.org/10.1207/s15516709cog2801_4)
39. Dominik Schlechtweg, Nina Tahmasebi, Simon Hengchen, Haim Dubossarsky, and Barbara McGillivray. 2021. DWUG: A large resource of diachronic word usage graphs in four languages. arXiv preprint arXiv:2104.08540. [↗](https://arxiv.org/abs/2104.08540)
40. Graham G Scott, Anne Keitel, Marc Becirspahic, Bo Yao, and Sara C Sereno. 2019. The glasgow norms: Ratings of 5,500 words on nine scales. Behavior research methods, 51(3):1258–1270. [↗](https://doi.org/10.3758/s13428-018-1099-3)
41. Laura J Speed and Marc Brybaert. 2021. Dutch sensory modality norms. Behavior Research Methods, pages 1–13. [↗](https://doi.org/10.3758/s13428-021-01656-9)
42. Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2020. Vl-bert: Pre-training of generic visual-linguistic representations. [↗](https://doi.org/10.48550/arxiv.1908.08530) [our card](https://md.research.elamur.ai/free/en/papers/su-2019-vl-bert-pre-training-generic/)
43. Ronen Tamari, Chen Shani, Tom Hope, Miriam R L Petruck, Omri Abend, and Dafna Shahaf. 2020. Language (re)modelling: Towards embodied language understanding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6268–6281, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ronen+Tamari%2C+Chen+Shani%2C+Tom+Hope%2C+Miriam+R+L+Petruck%2C+Omri+Abend%2C+and+Dafna+Shahaf%2E+2020%2E+Language+%28re%29modelling%3A+Towards+embodied+language+understanding%2E+In+Proceedings+of+the+58th+Annual+Meeting+o)
44. Bill Thompson and Gary Lupyan. 2018. Automatic estimation of lexical concreteness in 77 languages. In The 40th annual conference of the cognitive science society (cogsci 2018), pages 1122–1127. Cognitive Science Society. [find](https://scholar.google.com/scholar?q=Bill+Thompson+and+Gary+Lupyan%2E+2018%2E+Automatic+estimation+of+lexical+concreteness+in+77+languages%2E+In+The+40th+annual+conference+of+the+cognitive+science+society+%28cogsci+2018%29%2C+pages+1122%E2%80%931127%2E+Cognit)
45. Sean Trott and Benjamin Bergen. 2020. Why do human languages have homophones? Cognition, 205:104449. [↗](https://doi.org/10.1016/j.cognition.2020.104449)
46. Sean Trott and Benjamin Bergen. 2021. RAW-C: Relatedness of ambiguous words in context (a new lexical resource for English). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7077–7087, Online. Association for Computational Linguistics. [↗](https://doi.org/10.48448/fc6y-2r22)
47. Sean Trott, Tiago Timponi Torrent, Nancy Chang, and Nathan Schneider. 2020. (Re)construing meaning in NLP. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5170–5184, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sean+Trott%2C+Tiago+Timponi+Torrent%2C+Nancy+Chang%2C+and+Nathan+Schneider%2E+2020%2E+%28Re%29construing+meaning+in+NLP%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+p)
48. Jacob Turton, David Vinson, and Robert Smith. 2020. Extrapolating binder style word embeddings to new words. In Proceedings of the Second Workshop on Linguistic and Neurocognitive Resources, pages 1– 8, Marseille, France. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Jacob+Turton%2C+David+Vinson%2C+and+Robert+Smith%2E+2020%2E+Extrapolating+binder+style+word+embeddings+to+new+words%2E+In+Proceedings+of+the+Second+Workshop+on+Linguistic+and+Neurocognitive+Resources%2C+pages+1%E2%80%93+)
49. Akira Utsumi. 2020. Exploring what is encoded in distributional word vectors: A neurobiologically motivated analysis. Cognitive Science, 44(6):e12844. [↗](https://doi.org/10.1111/cogs.12844)
50. Mingyu Wan, Kathleen Ahrens, Emmanuele Chersoni, Menghan Jiang, Qi Su, Rong Xiang, and Chu-Ren Huang. 2020a. Using conceptual norms for metaphor detection. In Proceedings of the Second Workshop on Figurative Language Processing, pages 104–109, Online. Association for Computational Linguistics. [↗](https://doi.org/10.60692/c0f5x-h7283)
51. Mingyu Wan, Baixi Xing, Qi Su, Pengyuan Liu, and Chu-Ren Huang. 2020b. Sensorimotor enhanced neural network for metaphor detection. In Proceedings of the 34th Pacific Asia Conference on Language, Information and Computation, pages 312– 317, Hanoi, Vietnam. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mingyu+Wan%2C+Baixi+Xing%2C+Qi+Su%2C+Pengyuan+Liu%2C+and+Chu%2DRen+Huang%2E+2020b%2E+Sensorimotor+enhanced+neural+network+for+metaphor+detection%2E+In+Proceedings+of+the+34th+Pacific+Asia+Conference+on+Language%2C+Info)
52. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 353–355, Brussels, Belgium. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/w18-5446) [our card](https://md.research.elamur.ai/free/en/papers/wang-2018-glue-multi-task-benchmark-analysis/)
53. Cai Wingfield and Louise Connell. 2021. Sensorimotor distance: A fully grounded measure of semantic similarity for 800 million concept pairs. [find](https://scholar.google.com/scholar?q=Cai+Wingfield+and+Louise+Connell%2E+2021%2E+Sensorimotor+distance%3A+A+fully+grounded+measure+of+semantic+similarity+for+800+million+concept+pairs%2E)
54. Bodo Winter and Benjamin Bergen. 2012. Language comprehenders represent object distance both visually and auditorily. Language and Cognition, 4(1):1–16. [↗](https://doi.org/10.1515/langcog-2012-0001)
55. Eiling Yee and Sharon L Thompson-Schill. 2016. Putting concepts into context. Psychonomic bulletin & review, 23(4):1015–1027. [↗](https://doi.org/10.3758/s13423-015-0948-7)
56. Rowan Zellers, Ari Holtzman, Matthew Peters, Roozbeh Mottaghi, Aniruddha Kembhavi, Ali Farhadi, and Yejin Choi. 2021a. PIGLeT: Language grounding through neuro-symbolic interaction in a 3D world. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2040–2050, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Rowan+Zellers%2C+Ari+Holtzman%2C+Matthew+Peters%2C+Roozbeh+Mottaghi%2C+Aniruddha+Kembhavi%2C+Ali+Farhadi%2C+and+Yejin+Choi%2E+2021a%2E+PIGLeT%3A+Language+grounding+through+neuro%2Dsymbolic+interaction+in+a+3D+world%2E+In+P)
57. Rowan Zellers, Ximing Lu, Jack Hessel, Youngjae Yu, Jae Sung Park, Jize Cao, Ali Farhadi, and Yejin Choi. 2021b. Merlot: Multimodal neural script knowledge models. arXiv preprint arXiv:2106.02636. [↗](https://arxiv.org/abs/2106.02636)

*Updated 24 October 2026*