How does BERT capture semantics? A closer look at polysemous words
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
The recent paradigm shift to contextual word embeddings has seen tremendous success across a wide range of down-stream tasks.However, little is known on how the emergent relation of context and semantics manifests geometrically.We investigate polysemous words as one particularly prominent instance of semantic organization.Our rigorous quantitative analysis of linear separability and cluster organization in embedding vectors produced by BERT shows that semantics do not surface as isolated clusters but form seamless structures, tightly coupled with sentiment and syntax.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · 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) · doi:10.18653/v1/n19-1423 · Cited by 54,325
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222
(2019) · doi:10.18653/v1/p19-1356 · Cited by 1,291 · cited 2×
“In addition, the embedding space produced by BERT has been analyzed in terms of syntactic features, such as parse-trees (Coenen et al., 2019; Jawahar et al., 2019), part-of-speech, verbs and arguments (Shi et al., 2019; Ribeiro et al., 2019).”
BackgroundMethodEthayarajh, K. (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/d19-1006 · Cited by 841
On Measuring Social Biases in Sentence Encoders
May, C., Wang, A., Bordia, S., Bowman, S. R., & Rudinger, R. (2019) · 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) · doi:10.18653/v1/n19-1063 · Cited by 461 · cited 1×
“Certain combinations of semantics, syntax, and sentiment are more frequent than others (Hagoort, 2003; May et al., 2019), likely affecting the subspace structure and sometimes resulting in clusters that are distinct due to their simultaneous difference in both semantic and syntactic features (see…”
BackgroundIntegrating Selectional Constraints and Subcategorization Frames in a Dependency Parser
(2016) · HAL · doi:10.1162/coli · Cited by 135
Cited by
PTR: Prompt Tuning with Rules for Text Classification
Han, X., Zhao, W., Ding, N., Liu, Z., & Sun, M. (2021) · arXiv · doi:10.48550/arxiv.2105.11259 · Cited by 478
“, 2019), semantic (Yenicelik et al., 2020), syntactic (Hewitt and Manning, 2019) and world”
BackgroundKnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
Chen, X., Zhang, N., Xie, X., Deng, S., Yao, Y., Tan, C., Huang, F., Si, L., & Chen, H. (2022) · Proceedings of the ACM Web Conference 2022 · doi:10.1145/3485447.3511998 · Cited by 389
Sentiment analysis and opinion mining on educational data: A survey
Shaik, T., Tao, X., Dann, C., Xie, H., Li, Y., & Galligan, L. (2023) · Natural Language Processing Journal · doi:10.1016/j.nlp.2022.100003 · Cited by 215
LogFiT: Log Anomaly Detection Using Fine-Tuned Language Models
Almodovar, C., Sabrina, F., Karimi, S., & Azad, S. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3358730 · Cited by 111
“In contrast, LogFiT operates on well-formed sentences, leveraging its transformer architecture to understand both structural and semantic properties of log data [29], [30].”
Background
Metadata
- Authors
- Yenicelik, D., Schmidt, F., & Kilcher, Y.
- Venue
- Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
- Published
- 2020
- Pages
- 156-162
- OpenAlex
- W3102970018
- Cited by
- 50
- References
- 7
- FWCI
- 3.53
- 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: How does BERT capture semantics? A closer look at polysemous words. https://app.cochat.ai/papers/10.18653/v1/2020.blackboxnlp-1.15
- The paper
- Yenicelik, D., Schmidt, F., & Kilcher, Y. (2020). How does BERT capture semantics? A closer look at polysemous words. Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP. https://doi.org/10.18653/v1/2020.blackboxnlp-1.15
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.