How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings
Open accessAbstract
Replacing static word embeddings with contextualized word representations has yielded significant improvements on many NLP tasks.However, just how contextual are the contextualized representations produced by models such as ELMo and BERT?Are there infinitely many context-specific representations for each word, or are words essentially assigned one of a finite number of word-sense representations?For one, we find that the contextualized representations of all words are not isotropic in any layer of the contextualizing model.While representations of the same word in different contexts still have a greater cosine similarity than those of two different words, this self-similarity is much lower in upper layers.This suggests that upper layers of contextualizing models produce more context-specific representations, much like how upper layers of LSTMs produce more task-specific representations.In all layers of ELMo, BERT, and GPT-2, on average, less than 5% of the variance in a word's contextualized representations can be explained by a static embedding for that word, providing some justification for the success of contextualized representations.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Precedent exists for using PCA to extract network-level patterns from high-dimensional neural data, including fMRI, EEG, and LLM embeddings.
“Precedent exists for using PCA to extract network-level patterns from high-dimensional neural data, including fMRI (Smith et al., 2015), EEG (Blankertz et al., 2011), and even LLM embeddings (Ethayarajh, 2019).”
From Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis (2025) · cites this paper as Ethayarajh, 2019
Section 4.3 (page not available in our copy) uses the first principal component of contextualized BERT, ELMo, and GPT-2 word representations to create static embeddings. This supports a precedent for applying PCA to language-model embeddings, but the paper does not describe extracting network-level patterns. The fMRI and EEG examples are attributed to other citations in the sentence. (LLM, conf=0.86)
Experimental — accuracy not yet measuredEthayarajh (2019) notes that unidirectional models produce embeddings that vary smoothly across tokens, implying that the difference operation can still capture meaningful transitions within a span.
“Ethayarajh (2019) notes that unidirectional models produce embeddings that vary smoothly across tokens, implying that the difference operation can still capture meaningful transitions within a span.”
From Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis (2025) · cites this paper as Ethayarajh, 2019
Section 4.2 measures similarity among words in the same sentence, but does not examine whether embeddings change smoothly between successive tokens. Neither that section nor the passages found on vector geometry address whether subtracting embeddings captures meaningful transitions within a span (searched for unidirectional models, neighboring tokens, smooth variation, and differences). (LLM, conf=0.72)
Experimental — accuracy not yet measuredBERT embeddings capture rich semantic information and are widely recognized as effective for sentence similarity tasks.
“Previous literature showed the BERT embeddings54 capture rich semantic information and are widely recognized as effective for sentence similarity tasks55–57.”
From Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation (2025) · cites this paper as [57]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
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 48,293 · see citing works
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 · see citing works
Distributed 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 · see citing works
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515 · see citing works
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983 · see citing works
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687 · see citing works
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · see citing works
Linguistic Regularities in Continuous Space Word Representations
Mikolov, T., Yih, W.-T., & Zweig, G. (2013) · Cited by 2,913 · see citing works
Neural Word Embedding as Implicit Matrix Factorization
Levy, O., & Goldberg, Y. (2014) · neural information processing systems · Cited by 1,581 · see citing works
SimLex-999: Evaluating Semantic Models With (Genuine) Similarity Estimation
Hill, F., Reichart, R., & Korhonen, A. (2015) · Computational Linguistics · doi:10.1162/coli_a_00237 · Cited by 1,179 · see citing works
(2017) · International Conference on Learning Representations · Cited by 1,075 · see citing works
Placing search in context: the concept revisited.
Finkelstein, L., Gabrilovich, E., Matias, Y., Rivlin, E., Solan, Z., Wolfman, G., & Ruppin, E. (2002) · Cited by 939 · see citing works
Multimodal Distributional Semantics
Bruni, E., Tran, N. K., & Baroni, M. (2014) · Journal of Artificial Intelligence Research · doi:10.1613/jair.4135 · Cited by 910 · see citing works
Better Word Representations with Recursive Neural Networks for Morphology
Luong, M.-T., Socher, R., & Manning, C. D. (2013) · Conference on Computational Natural Language Learning · Cited by 789 · see citing works
SemEval-2012 Task 6: A Pilot on Semantic Textual Similarity
Agirre, E., Cer, D. M., Diab, M., & González-Agirre, A. (2012) · Cited by 653 · see citing works
Linguistic Knowledge and Transferability of Contextual Representations
Liu, N. F., Gardner, M., Belinkov, Y., Peters, M. E., & Smith, N. A. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1112 · Cited by 651 · see citing works
Linguistic Regularities in Sparse and Explicit Word Representations
Levy, O., & Goldberg, Y. (2014) · Conference on Computational Natural Language Learning · doi:10.3115/v1/w14-1618 · Cited by 622 · see citing works
SemEval-2014 Task 10: Multilingual Semantic Textual Similarity
Agirre, E., Banea, C., Cardie, C., Cer, D. M., Diab, M., González-Agirre, A., Guo, W., Mihalcea, R. F., Rigau, G., & Wiebe, J. (2014) · International Workshop on Semantic Evaluation (SemEval) · doi:10.3115/v1/s14-2010 · Cited by 492 · see citing works
SemEval-2015 Task 2: Semantic Textual Similarity, English, Spanish and Pilot on Interpretability
Agirre, E., Banea, C., Cardie, C., Cer, D. M., Diab, M., González-Agirre, A., Guo, W., López-Gazpio, I., Maritxalar, M., Mihalcea, R. F., et al. (2015) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/s15-2045 · Cited by 488 · see citing works
How we BLESSed distributional semantic evaluation
Baroni, M., & Lenci, A. (2011) · Cited by 282 · see citing works
SemEval-2012 Task 2 : measuring degrees of relational similarity
Jurgens, D., Turney, P. D., Mohammad, S. M., & Holyoak, K. J. (2012) · NPARC · Cited by 182 · see citing works
All-but-the-Top: Simple and Effective Postprocessing for Word RepresentationsPreprint
Mu, J., Bhat, S., & Viswanath, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.01417 · Cited by 126 · see citing works
All-but-the-Top: Simple and Effective Postprocessing for Word RepresentationsPreprint
Mu, J., & Viswanath, P. (2018) · arXiv (Cornell University) · Cited by 120 · see citing works
The strange geometry of skip-gram with negative sampling
Mimno, D., & Thompson, L. (2017) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d17-1308 · Cited by 104 · see citing works
Attribute-Based and Value-Based Clustering: An Evaluation.
Almuhareb, A., & Poesio, M. (2004) · Iris (University of Trento) · Cited by 97 · see citing works
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
Flagged first, then by citations
1 of the 27 references couldn’t be matched to a known paper.
Research works printed but not linked: 5
- Eneko Agirre, Daniel Cer, Mona Diab, Aitor Gonzalez- Agirre, and Weiwei Guo. 2013. Sem 2013 shared task: Semantic textual similarity, including a pilot on typed-similarity. In SEM 2013: The Second Joint Conference on Lexical and Computational Seman- tics. Association for Computational Linguistics.
- John Hewitt and Christopher D. Manning. 2019. A structural probe for finding syntax in word represen- tations. In North American Chapter of the Associ- ation for Computational Linguistics: Human Lan- guage Technologies. Association for Computational Linguistics.
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Cor- rado, and Jeff Dean. 2013a. Distributed representa- tions of words and phrases and their compositional- ity. In Advances in Neural Information Processing Systems. pages 3111-3119.
- Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word rep- resentations. In Proceedings of the 2018 Confer- ence of the North American Chapter of the Associ- ation for Computational Linguistics: Human Lan- guage Technologies, Volume 1 (Long Papers). pages 2227-2237.
- Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R. Thomas McCoy, Najoung Kim, Benjamin Van Durme, Samuel R. Bowman, Dipan- jan Das, and Ellie Pavlick. 2019. What do you learn from context? probing for sentence structure in contextualized word representations. In Inter- national Conference on Learning Representations. https://openreview.net/forum?id=SJzSgnRcKX.
Cited by
Sorted by citations
SimCSE: Simple Contrastive Learning of Sentence Embeddings
Gao, T., Yao, X., & Chen, D. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.552 · Cited by 2,851 · see citing works
A Metaverse: Taxonomy, Components, Applications, and Open Challenges
Park, S., & Kim, Y. (2022) · IEEE Access · doi:10.1109/access.2021.3140175 · Cited by 1,926 · see citing works
A survey on sentiment analysis methods, applications, and challenges
Wankhade, M., Rao, A. C. S., & Kulkarni, C. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10144-1 · Cited by 1,728 · see citing works
A primer in BERTology: What we know about how BERT works
Rogers, A., Kovaleva, O., & Rumshisky, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00349 · Cited by 1,552 · see citing works
Pre-trained models: Past, present and future
Han, X., Zhang, Z., Ding, N., Gu, Y., Liu, X., Huo, Y., Qiu, J., Yao, Y., Zhang, A., Zhang, L., et al. (2021) · AI Open · doi:10.1016/j.aiopen.2021.08.002 · Cited by 994 · see citing works
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 · see citing works
Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
Qiu, R., Huang, Z. H., Yin, H., & Wang, Z. (2022) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3488560.3498433 · Cited by 497 · see citing works
Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models
Ni, J., Ábrego, G. H., Constant, N., Ma, J., Hall, K., Cer, D. M., & Yang, Y. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.146 · Cited by 449 · see citing works
Shared computational principles for language processing in humans and deep language models
Goldstein, A., Zada, Z., Buchnik, E., Schain, M., Price, A., Aubrey, B., Nastase, S. A., Feder, A., Emanuel, D., Cohen, A., et al. (2022) · Nature Neuroscience · doi:10.1038/s41593-022-01026-4 · Cited by 447 · see citing works
BERTology Meets Biology: Interpreting Attention in Protein Language Models
Vig, J., Madani, A., Varshney, L. R., Xiong, C., Socher, R., & Rajani, N. F. (2020) · doi:10.1101/2020.06.26.174417 · Cited by 338 · see citing works
Intelligent Computing: The Latest Advances, Challenges, and Future
Zhu, S., Yu, T., Xu, T., Chen, H., Dustdar, S., Gigan, S., Gündüz, D., Hossain, E., Jin, Y., Lin, F., et al. (2023) · Intelligent Computing · doi:10.34133/icomputing.0006 · Cited by 319 · see citing works
Whitening Sentence Representations for Better Semantics and Faster RetrievalPreprint
Su, J., Cao, J., Liu, W., & Ou, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.15316 · Cited by 308 · see citing works
A Survey on Text Classification Algorithms: From Text to Predictions
Gasparetto, A., Marcuzzo, M., Zangari, A., & Albarelli, A. (2022) · Information · doi:10.3390/info13020083 · Cited by 278 · see citing works
Layer-Wise Analysis of a Self-Supervised Speech Representation Model
Pasad, A., Chou, J.-C., & Livescu, K. (2021) · 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · doi:10.1109/asru51503.2021.9688093 · Cited by 262 · see citing works
A comparative study of automated legal text classification using random forests and deep learning
Chen, H., Wu, L., Chen, J., Lu, W. P., & Ding, J. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102798 · Cited by 248 · see citing works
A Review on Word Embedding Techniques for Text Classification
Birunda, S. S., & Devi, R. K. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-15-9651-3_23 · Cited by 224 · see citing works
Exploring the Potential of Large Language Models (LLMs)in Learning on Graphs
Chen, Z., Mao, H., Li, H., Jin, W., Wen, H., Wei, X., Wang, S., Yin, D., Fan, W., Liu, H., et al. (2024) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3655103.3655110 · Cited by 209 · see citing works
Probing Pretrained Language Models for Lexical Semantics
Vulić, I., Ponti, E. M., Litschko, R., Glavaš, G., & Korhonen, A. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.586 · Cited by 185 · see citing works
Guo, W., & Caliskan, A. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462536 · Cited by 180 · see citing works
SBERT-WK: A Sentence Embedding Method by Dissecting BERT-Based Word Models
Wang, B., & Kuo, C. ‐. J. (2020) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2020.3008390 · Cited by 179 · see citing works
PromptBERT: Improving BERT Sentence Embeddings with Prompts
Jiang, T., Jiao, J., Huang, S., Zhang, Z., Wang, D., Zhuang, F., Wei, F., Huang, H., Deng, D., & Zhang, Q. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.603 · Cited by 173 · see citing works
Zhang, H., & Shafiq, M. O. (2024) · Journal Of Big Data · doi:10.1186/s40537-023-00842-0 · Cited by 164 · see citing works
Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer
Powalski, R., Borchmann, Ł., Jurkiewicz, D., Dwojak, T., Pietruszka, M., & Pałka, G. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86331-9_47 · Cited by 163 · see citing works
Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings
Bommasani, R., Davis, K., & Cardie, C. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.431 · Cited by 147 · see citing works
Applications of natural language processing and large language models in materials discovery
Jiang, X., Wang, W., Tian, S., Wang, H., Lookman, T., & Su, Y. (2025) · npj Computational Materials · doi:10.1038/s41524-025-01554-0 · Cited by 145 · see citing works
A survey on deep learning for patent analysis
Krestel, R., Chikkamath, R., Hewel, C., & Risch, J. (2021) · World Patent Information · doi:10.1016/j.wpi.2021.102035 · Cited by 143 · see citing works
Towards Faithful Model Explanation in NLP: A Survey
Lyu, Q., Apidianaki, M., & Callison-Burch, C. (2024) · Computational Linguistics · doi:10.1162/coli_a_00511 · Cited by 143 · see citing works
COCO-LM: Correcting and Contrasting Text Sequences for Language Model PretrainingPreprint
Yu, M., Xiong, C., Bajaj, P., Tiwary, S., Bennett, P. N., Han, J., & Song, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.08473 · Cited by 133 · see citing works
Word meaning in minds and machines.
Lake, B. M., & Murphy, G. L. (2023) · Psychological Review · doi:10.1037/rev0000297 · Cited by 131 · see citing works
Li, Z., Zou, Y., Zhang, C., Zhang, Q., & Wei, Z. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.22 · Cited by 129 · see citing works
Pretrained domain-specific language model for natural language processing tasks in the AEC domain
Zheng, Z., Lu, X., Chen, K., Zhou, Y., & Lin, J. (2022) · Computers in Industry · doi:10.1016/j.compind.2022.103733 · Cited by 129 · see citing works
PyMT5: multi-mode translation of natural language and Python code with transformers
Clement, C. B., Drain, D., Timcheck, J., Svyatkovskiy, A., & Sundaresan, N. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.728 · Cited by 123 · see citing works
Machine/Deep Learning for Software Engineering: A Systematic Literature Review
Wang, S., Huang, L., Gao, A., Ge, J., Zhang, T., Feng, H., Satyarth, I., Li, M., Zhang, H., & Ng, V. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2022.3173346 · Cited by 111 · see citing works
Zero-shot learning for requirements classification: An exploratory study
Alhoshan, W., Ferrari, A., & Zhao, L. (2023) · Information and Software Technology · doi:10.1016/j.infsof.2023.107202 · Cited by 109 · see citing works
DNA language model GROVER learns sequence context in the human genome
Sanabria, M., Hirsch, J., Joubert, P. M., & Poetsch, A. R. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00872-0 · Cited by 108 · see citing works
A Survey on Machine Reading Comprehension Systems
Baradaran, R., Ghiasi, R., & Amirkhani, H. (2022) · Natural Language Engineering · doi:10.1017/s1351324921000395 · Cited by 101 · see citing works
Liu, F., Vulić, I., Korhonen, A., & Collier, N. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.109 · Cited by 93 · see citing works
Wan, Y., Zhao, W., Zhang, H., Sui, Y., Xu, G., & Jin, H. (2022) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3510003.3510050 · Cited by 91 · see citing works
Do large language models resemble humans in language use?Preprint
Cai, Z. G., Duan, X., Haslett, D. A., Wang, S., & Pickering, M. J. (2023) · doi:10.31234/osf.io/s49qv · Cited by 90 · see citing works
Pham, T. M., Bui, T., Mai, L., & Nguyen, A. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.98 · Cited by 89 · see citing works
Ceasing hate with MoH: Hate Speech Detection in Hindi–English code-switched language
Sharma, A., Kabra, A., & Jain, M. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102760 · Cited by 88 · see citing works
Bonikowski, B., Luo, Y., & Stuhler, O. (2022) · Sociological Methods & Research · doi:10.1177/00491241221122317 · Cited by 88 · see citing works
A comparative evaluation and analysis of three generations of Distributional Semantic Models
Lenci, A., Sahlgren, M., Jeuniaux, P. P. J. M. H., Gyllensten, A. C., & Miliani, M. (2022) · Language Resources and Evaluation · doi:10.1007/s10579-021-09575-z · Cited by 83 · see citing works
Attention Mechanism, Transformers, BERT, and GPT: Tutorial and SurveyPreprint
Ghojogh, B., & Ghodsi, A. (2020) · doi:10.31219/osf.io/m6gcn · Cited by 82 · see citing works
Inductive Entity Representations from Text via Link Prediction
Daza, D., Cochez, M., & Groth, P. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3450141 · Cited by 81 · see citing works
AI-Enabled Automation for Completeness Checking of Privacy Policies
Amaral, O., Abualhaija, S., Torre, D., Sabetzadeh, M., & Briand, L. (2021) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2021.3124332 · Cited by 81 · see citing works
Large language models for medicine: a survey
Zheng, Y., Gan, W., Chen, Z., Qi, Z., Liang, Q., & Yu, P. S. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02318-w · Cited by 81 · see citing works
GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP
Khondaker, M. T. I., Waheed, A., Nagoudi, E. M. B., & Abdul-Mageed, M. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.16 · Cited by 79 · see citing works
Analysis and Evaluation of Language Models for Word Sense Disambiguation
Loureiro, D., Rezaee, K., Pilehvar, M. T., & Camacho-Collados, J. (2021) · Computational Linguistics · doi:10.1162/coli_a_00405 · Cited by 78 · see citing works
Electric Power Audit Text Classification With Multi-Grained Pre-Trained Language Model
Meng, Q., Song, Y., Mu, J., Lv, Y., Yang, J., Xu, L., Zhao, J., Ma, J., Yao, W., Wang, R., et al. (2023) · IEEE Access · doi:10.1109/access.2023.3240162 · Cited by 78 · see citing works
Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words
Zhou, K., Ethayarajh, K., Card, D., & Jurafsky, D. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-short.45 · Cited by 76 · see citing works
Self-citationTowards a holistic framework for multimodal LLM in 3D brain CT radiology report generation
Li, C.-Y., Chang, K.-J., Yang, C.-F., Wu, H.-Y., Chen, W., Bansal, H., Chen, L., Yang, Y.-P., Chen, Y.-C., Chen, S.-P., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-57426-0 · Cited by 75 · see citing works
“This list is not merely a compilation of keywords but also includes synonyms, enabling the system to recognize a broader array of related terms that may appear in different contexts.”
Contextual and Non-Contextual Word Embeddings: an in-depth Linguistic Investigation
Miaschi, A., & Dell’Orletta⋄, F. (2020) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/2020.repl4nlp-1.15 · Cited by 75 · see citing works
Timkey, W., & van Schijndel, M. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.372 · Cited by 75 · see citing works
Evolving techniques in sentiment analysis: a comprehensive review
Kumar, M., Khan, L., & Chang, H.-T. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2592 · Cited by 75 · see citing works
Open Vocabulary Electroencephalography-to-Text Decoding and Zero-Shot Sentiment Classification
Wang, Z., & Ji, H. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i5.20472 · Cited by 74 · see citing works
Analyzing Redundancy in Pretrained Transformer Models
Dalvi, F., Sajjad, H., Durrani, N., & Belinkov, Y. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.398 · Cited by 71 · see citing works
Multi-SimLex: A Large-Scale Evaluation of Multilingual and Crosslingual Lexical Semantic Similarity
Vulić, I., Baker, S., Ponti, E. M., Petti, U., Leviant, I., Wing, K., Majewska, O., Bar, E., Malone, M., Poibeau, T., et al. (2020) · Computational Linguistics · doi:10.1162/coli_a_00391 · Cited by 71 · see citing works
X-Class: Text Classification with Extremely Weak Supervision
Wang, Z., Mekala, D., & Shang, J. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.242 · Cited by 70 · see citing works
On cross-lingual retrieval with multilingual text encoders
Litschko, R., Vulić, I., Ponzetto, S. P., & Glavaš, G. (2022) · Information Retrieval · doi:10.1007/s10791-022-09406-x · Cited by 70 · see citing works
Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar InductionPreprint
Kim, T., Choi, J., Edmiston, D., & Lee, S.-G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.00737 · Cited by 70 · see citing works
Analyzing Transformers in Embedding Space
Dar, G., Geva, M., Gupta, A., & Berant, J. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.893 · Cited by 69 · see citing works
On reading and interpreting black box deep neural networks
Dobson, J. E. (2023) · International Journal of Digital Humanities · doi:10.1007/s42803-023-00075-w · Cited by 67 · see citing works
Goldstein, A., Grinstein-Dabush, A., Schain, M., Wang, H., Hong, Z., Aubrey, B., Nastase, S. A., Zada, Z., Ham, E., Feder, A., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-46631-y · Cited by 64 · see citing works
Extracting Latent Steering Vectors from Pretrained Language Models
Subramani, N., Suresh, N., & Peters, M. E. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.48 · Cited by 63 · see citing works
Topic Modeling with Contextualized Word Representation ClustersPreprint
Thompson, L., & Mimno, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12626 · Cited by 63 · see citing works
Terminology and Lexicography Research and Practice
Goyens, M., Ducos, J., Vigneron, F., & Fourneau, I. (2013) · Terminology and lexicography research and practice · doi:10.1075/tlrp · Cited by 63 · see citing works
Alshattnawi, S., Shatnawi, A., Alsobeh, A., & Magableh, A. A. A. R. (2024) · Applied Sciences · doi:10.3390/app14062254 · Cited by 58 · see citing works
Contextual feature extraction hierarchies converge in large language models and the brain
Mischler, G., Li, Y. A., Bickel, S., Mehta, A. D., & Mesgarani, N. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00925-4 · Cited by 58 · see citing works
Let’s Play Mono - Poly : BERT Can Reveal Words’ Polysemy Level and Partitionability into Senses
Soler, A. G., & Apidianaki, M. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00400 · Cited by 58 · see citing works
Inducing Language-Agnostic Multilingual Representations
Zhao, W., Eger, S., Bjerva, J., & Augenstein, I. (2021) · Joint Conference on Lexical and Computational Semantics · doi:10.18653/v1/2021.starsem-1.22 · Cited by 57 · see citing works
Isotropy in the Contextual Embedding Space: Clusters and Manifolds
Cai, X., Huang, J., Bian, Y., & Church, K. (2021) · International Conference on Learning Representations · Cited by 55 · see citing works
Crafting clarity: Leveraging large language models to decode consumer reviews
Praveen, S. V., Gajjar, P., Ray, R. K., & Dutt, A. (2024) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2024.103975 · Cited by 55 · see citing works
LawLLM: Law Large Language Model for the US Legal System
Shu, D., Zhao, H., Liu, X., Demeter, D., Du, M., & Zhang, Y. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3680020 · Cited by 55 · see citing works
A Survey on Sentiment Analysis and Opinion Mining in Greek Social Media
Alexandridis, G., Varlamis, I., Korovesis, K., Caridakis, G., & Tsantilas, P. (2021) · Information · doi:10.3390/info12080331 · Cited by 55 · see citing works
Unsupervised Sentence Representation via Contrastive Learning with Mixing Negatives
Zhang, Y., Zhang, R., Mensah, S., Liu, X., & Mao, Y. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21428 · Cited by 54 · see citing works
Optimization techniques for sentiment analysis based on LLM (GPT-3)
Zhan, T., Shi, C., Shi, Y., Li, H., & Lin, Y. (2024) · Applied and Computational Engineering · doi:10.54254/2755-2721/67/2024ma0060 · Cited by 54 · see citing works
Improving Neural Language Generation with Spectrum Control
Wang, L., Huang, J., Huang, K., Hu, Z., Wang, G., & Gu, Q. (2020) · International Conference on Learning Representations · Cited by 53 · see citing works
Similarity Analysis of Contextual Word Representation Models
Wu, J., Belinkov, Y., Sajjad, H., Durrani, N., Dalvi, F., & Glass, J. R. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.422 · Cited by 52 · see citing works
Retrieving Complex Tables with Multi-Granular Graph Representation Learning
Wang, F., Sun, K., Chen, M., Pujara, J., & Szekely, P. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3462909 · Cited by 52 · see citing works
TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning
Su, Y., Liu, F., Meng, Z., Lan, T., Shu, L., Shareghi, E., & Collier, N. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.191 · Cited by 52 · see citing works
CTRAN: CNN-Transformer-based network for natural language understanding
Rafiepour, M., & Sartakhti, J. S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107013 · Cited by 52 · see citing works
Dynamic Contextualized Word Embeddings
Hofmann, V., Pierrehumbert, J. B., & Schütze, H. (2021) · doi:10.18653/v1/2021.acl-long.542 · Cited by 52 · see citing works
The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes
Reimers, N., & Gurevych, I. (2021) · doi:10.18653/v1/2021.acl-short.77 · Cited by 52 · see citing works
Short-Text Semantic Similarity (STSS): Techniques, Challenges and Future Perspectives
Amur, Z. H., Hooi, Y. K., Bhanbhro, H., Dahri, K., & Soomro, G. M. (2023) · Applied Sciences · doi:10.3390/app13063911 · Cited by 51 · see citing works
Lee, M. H. J., Montgomery, J., & Lai, C. K. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658975 · Cited by 51 · see citing works
How does BERT capture semantics? A closer look at polysemous words
Yenicelik, D., Schmidt, F., & Kilcher, Y. (2020) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2020.blackboxnlp-1.15 · Cited by 51 · see citing works
Thinking ahead: spontaneous prediction in context as a keystone of language in humans and machinesPreprint
Goldstein, A., Zada, Z., Buchnik, E., Schain, M., Price, A. R., Aubrey, B., Nastase, S. A., Feder, A., Emanuel, D., Cohen, A., et al. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.12.02.403477 · Cited by 51 · see citing works
Contrastive Learning Models for Sentence Representations
Xu, L., Xie, H., Li, Z., Wang, F. L., Wang, W., & Li, Q. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3593590 · Cited by 50 · see citing works
A Closer Look at How Fine-tuning Changes BERT
Zhou, Y., & Srikumar, V. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.75 · Cited by 50 · see citing works
Semantics and Content-Based Recommendations
Musto, C., de Gemmis, M., Lops, P., Narducci, F., & Semeraro, G. M. (2012) · Springer eBooks · doi:10.1007/978-1-0716-2197-4_7 · Cited by 50 · see citing works
XRR: Extreme multi-label text classification with candidate retrieving and deep ranking
Xiong, J., Li, Y., Niu, X., & Leng, Y. (2022) · Information Sciences · doi:10.1016/j.ins.2022.11.158 · Cited by 50 · see citing works
Which *BERT? A Survey Organizing Contextualized Encoders
Xia, P., Wu, S., & Durme, B. V. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.608 · Cited by 50 · see citing works
Superbizarre Is Not Superb: Derivational Morphology Improves BERT’s Interpretation of Complex Words
Hofmann, V., Pierrehumbert, J. B., & Schütze, H. (2021) · doi:10.18653/v1/2021.acl-long.279 · Cited by 48 · see citing works
CoSENT: Consistent Sentence Embedding via Similarity Ranking
Huang, X., Peng, H., Zou, D., Liu, Z., Li, J., Liu, K., Wu, J. X., Su, J., & Yu, P. S. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3402087 · Cited by 46 · see citing works
Shi, H. H., Fang, L., Chen, X., Gu, C., Ma, K., Zhang, X., Zhang, Z., Gu, J., & Lim, E. G. (2024) · IET Smart Grid · doi:10.1049/stg2.12191 · Cited by 46 · see citing works
Embedding Refinement Framework for Targeted Aspect-Based Sentiment Analysis
Liang, B., Yin, R., Du, J., Gui, L., He, Y., Yang, M., & Xu, R. (2021) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2021.3071388 · Cited by 46 · see citing works
Ganesan, A. V., Matero, M., Ravula, A. R., Vu, H., & Schwartz, H. A. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.357 · Cited by 46 · see citing works
- Authors
- Ethayarajh, K.
- Affiliations
- Stanford University (US)
- Corresponding author
- Ethayarajh, Kawin
- Venue
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Published
- 2019
- Pages
- 55-65
- OpenAlex
- W2971569798
- Cited by
- 841
- References
- 27
- Citations by year
- 2026: 93 · 2025: 92 · 2024: 115 · 2023: 160 · 2022: 158 · 2021: 157 · 2020: 64 · 2013: 1 · 2012: 1
- FWCI
- 36.26
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Natural Sciences and Engineering Research Council of Canada
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- contextualized word representations, word embeddings, BERT, ELMo, GPT-2, embedding geometry, cosine similarity, static embeddings, layer-wise analysis
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
