Exploring Numeracy in Word Embeddings
Open accessThe DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
Word embeddings are now pervasive across NLP subfields as the de-facto method of forming text representataions.In this work, we show that existing embedding models are inadequate at constructing representations that capture salient aspects of mathematical meaning for numbers, which is important for language understanding.Numbers are ubiquitous and frequently appear in text.Inspired by cognitive studies on how humans perceive numbers, we develop an analysis framework to test how well word embeddings capture two essential properties of numbers: magnitude (e.g.3<4) and numeration (e.g.3=three).Our experiments reveal that most models capture an approximate notion of magnitude, but are inadequate at capturing numeration.We hope that our observations provide a starting point for the development of methods which better capture numeracy in NLP systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Within the context of pre-trained LMs, researchers have found that pre-trained embeddings and LMs can perform simple operations such as addition and subtraction when the number of digits is small but fail when the numbers are larger [9,88,139].”
From Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2023) · cites this paper as [88]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 1×
“GloVe (Pennington et al., 2014): Embeddings”
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 4×
“Skipgram (Mikolov et al., 2013a): Feedforward network trained to predict words within a fixed window surrounding the current word, with hidden weights used as embeddings.”
BackgroundMethodInfluentialDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
Enriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645 · cited 1×
“FastText (Bojanowski et al., 2017): Extended Skipgram model representing words as character n-grams to incorporate sub-word information.”
MethodA unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058 · cited 1×
“They have been a driving force in NLP in recent years, and enjoy widespread use in a variety of semantic tasks (Rumelhart et al.; Mikolov et al., 2013a,b; Collobert and Weston, 2008; Glorot et al., 2011; Turney and Pantel, 2010; Turney, 2013).”
BackgroundHarris, Z. S. (1954) · WORD · doi:10.1080/00437956.1954.11659520 · Cited by 4,807
Linguistic Regularities in Continuous Space Word Representations
Mikolov, T., Yih, W.-T., & Zweig, G. (2013) · North American Chapter of the Association for Computational Linguistics · Cited by 2,912
From Frequency to Meaning: Vector Space Models of Semantics
Turney, P. D., & Pantel, P. (2010) · Journal of Artificial Intelligence Research · doi:10.1613/jair.2934 · Cited by 2,866 · cited 1×
“They have been a driving force in NLP in recent years, and enjoy widespread use in a variety of semantic tasks (Rumelhart et al.; Mikolov et al., 2013a,b; Collobert and Weston, 2008; Glorot et al., 2011; Turney and Pantel, 2010; Turney, 2013).”
BackgroundFeigenson, L., Dehaene, S., & Spelke, E. (2004) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2004.05.002 · Cited by 2,466
Research works printed but not linked: 3
- [16]16. Marie-Catherine Marneffe, Anna N Rafferty, and Christopher D Manning. 2008. Finding contradic- tions in text. Proceedings of ACL-08: HLT, pages 1039-1047.
- [18]18. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Cor- rado, and Jeff Dean. 2013b. Distributed representa- tions of words and phrases and their compositional- ity. In Advances in neural information processing systems, pages 3111-3119.
- [28]28. Peter D Turney and Patrick Pantel. 2010. From fre- quency to meaning: Vector space models of se- mantics. Journal of artificial intelligence research, 37:141-188.
Cited by
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361
“Within the context of pre-trained LMs, researchers have found that pre-trained embeddings and LMs can perform simple operations such as addition and subtraction when the number of digits is small but fail when the numbers are larger [9, 88, 139].”
BackgroundLiu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352
“Within the context of pre-trained LMs, researchers have found that pre-trained embeddings and LMs can perform simple operations such as addition and subtraction when the number of digits is small but fail when the numbers are larger [9, 88, 139].”
BackgroundDo NLP Models Know Numbers? Probing Numeracy in Embeddings
Wallace, E., Wang, Y., Li, S., Singh, S., & Gardner, M. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1534 · Cited by 227
“In concurrent work, Naik et al. (2019) also explore numeracy in word vectors.”
BackgroundHanna, M., Liu, O., & Variengien, A. (2023) · arXiv · doi:10.48550/arxiv.2305.00586 · Cited by 84
“Some studies do examine the structure of number representations in pre-trained models [30, 49]; however, they do not provide a causal explanation about how these models leverage these representations to perform math.”
BackgroundINFOTABS: Inference on Tables as Semi-structured Data
Gupta, V., Mehta, M., Nokhiz, P., & Srikumar, V. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.210 · Cited by 77
Metadata
- Authors
- Naik, A., Ravichander, A., Rose, C., & Hovy, E.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Published
- 2019
- Pages
- 3374-3380
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2950645060
- Cited by
- 49
- References
- 33
- Citations by year
- 2026: 1 · 2025: 2 · 2024: 3 · 2023: 6 · 2022: 9 · 2021: 17 · 2020: 9 · 2019: 2
- FWCI
- 3.46
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- word embeddings, numeracy, numbers, number magnitude, numeration, approximate number system, text representation, language comprehension, cognitive linguistics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Exploring Numeracy in Word Embeddings. https://app.cochat.ai/papers/10.18653/v1/p19-1329
- The paper
- Naik, A., Ravichander, A., Rose, C., & Hovy, E. (2019). Exploring Numeracy in Word Embeddings. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1329
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.