Towards Understanding Linear Word Analogies
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
A surprising property of word vectors is that word analogies can often be solved with vector arithmetic.However, it is unclear why arithmetic operators correspond to non-linear embedding models such as skip-gram with negative sampling (SGNS).We provide a formal explanation of this phenomenon without making the strong assumptions that past theories have made about the vector space and word distribution.Our theory has several implications.Past work has conjectured that linear substructures exist in vector spaces because relations can be represented as ratios; we prove that this holds for SGNS.We provide novel justification for the addition of SGNS word vectors by showing that it automatically downweights the more frequent word, as weighting schemes do ad hoc.Lastly, we offer an information theoretic interpretation of Euclidean distance in vector spaces, justifying its use in capturing word dissimilarity.
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.
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
Landauer, T. K., & Dumais, S. T. (1997) · Psychological Review · doi:10.1037/0033-295x.104.2.211 · Cited by 6,282
A 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
A Latent Variable Model Approach to PMI-based Word Embeddings
Arora, S., Li, Y., Liang, Y., Ma, T., & Risteski, A. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00106 · Cited by 286 · cited 3×
“The latent variable model (Arora et al., 2016) was the first attempt at rigorously explaining why word analogies can be solved arithmetically.”
Influential
Cited by
On the Sentence Embeddings from Pre-trained Language Models
Li, B., Zhou, H., He, J., Wang, M., Yang, Y., & Li, L. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.733 · Cited by 593
Artificial Intelligence in mental health and the biases of language based models
Straw, I., & Callison-Burch, C. (2020) · PLOS ONE · doi:10.1371/journal.pone.0240376 · Cited by 164
Utility is in the Eye of the User: A Critique of NLP Leaderboards
Ethayarajh, K., & Jurafsky, D. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.393 · Cited by 147
Self-citationAnalogies minus analogy test: measuring regularities in word embeddings
Fournier, L., Dupoux, E., & Dunbar, E. (2020) · Proceedings of the 24th Conference on Computational Natural Language Learning · doi:10.18653/v1/2020.conll-1.29 · Cited by 19
Is Your Classifier Actually Biased? Measuring Fairness under Uncertainty with Bernstein Bounds
Ethayarajh, K. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.262 · Cited by 12
Self-citation
Metadata
- Authors
- Ethayarajh, K., Duvenaud, D., & Hirst, G.
- Venue
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Published
- 2019
- Pages
- 3253-3262
- OpenAlex
- W2896232552
- Cited by
- 81
- References
- 3
- FWCI
- 5.31
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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: Towards Understanding Linear Word Analogies. https://app.cochat.ai/papers/10.18653/v1/p19-1315
- The paper
- Ethayarajh, K., Duvenaud, D., & Hirst, G. (2019). Towards Understanding Linear Word Analogies. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1315
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.