The DOI matches its Crossref record; 26 of the 27 references it cites were found in a registry or an index.
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.
Overview
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
Verification
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“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
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“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
Experimental — accuracy not yet measuredIn the citing paper
“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.
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
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
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
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
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
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
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
Linguistic Regularities in Continuous Space Word Representations
Mikolov, T., Yih, W.-T., & Zweig, G. (2013) · Cited by 2,913
Neural Word Embedding as Implicit Matrix Factorization
Levy, O., & Goldberg, Y. (2014) · neural information processing systems · Cited by 1,581
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
Items 401–500 of 898
Xiao, C., Long, Y., & Moubayed, N. A. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.778 · Cited by 10
INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation
Zhu, W., Xu, J., Huang, S., Kong, L., & Chen, J. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.888 · Cited by 6
Lexical Semantics with Large Language Models: A Case Study of English “break”
Petersen, E., & Potts, C. (2023) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2023.findings-eacl.36 · Cited by 10
DagoBERT: Generating Derivational Morphology with a Pretrained Language Model
Hofmann, V., Pierrehumbert, J. B., & Schütze, H. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.316 · Cited by 9
Short-text intention recognition based on multi-dimensional dynamic word vectors
Xiao, M., Yao, M., & Li, Y. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1678/1/012080 · Cited by 6
Comparing Dependency-based Compositional Models with Contextualized Word Embeddings
Gamallo, P., Prada-Corral, M., & García, M. (2021) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0010391812581265 · Cited by 6
Strings and Things: A Semantic Search Engine for news quotes using Named Entity Recognition
Kostakos, P. (2020) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam49781.2020.9381383 · Cited by 6
Exploring the Combination of Contextual Word Embeddings and Knowledge Graph EmbeddingsPreprint
Dieudonat, L., Han, K., Leavitt, P., & Marquer, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.08371 · Cited by 8
Patterns of Lexical Ambiguity in Contextualised Language ModelsPreprint
Haber, J., & Poesio, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.13032 · Cited by 6
Synwmd: Syntax-Aware Word Mover's Distance for Sentence Similarity EvaluationPreprint
Wei, C., Wang, B., & Kuo, C. ‐. J. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4145635 · Cited by 6
Inducing state anxiety in LLM agents reproduces human-like biases in consumer decision-making
Ben‐Zion, Z., Elyoseph, Z., Spiller, T. R., & Lazebnik, T. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00122-1 · Cited by 8
Mikkelsen, Y. (2026) · JMIR Medical Informatics · doi:10.2196/94241 · Cited by 6
Measuring Lexico-Semantic Alignment in Debates with Contextualized Word Representations
Soler, A. G., Labeau, M., & Clavel, C. (2023) · Workshop on Social Influence in Conversations (SICon) · doi:10.18653/v1/2023.sicon-1.6 · Cited by 5
SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings
Engler, J., Sikdar, S., Lutz, M., & Strohmaier, M. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.338 · Cited by 7
Evaluating Bert and GPT-2 Models for Personalised Linkedin Post Recommendation
Singh, P., Jain, B., & Sinha, K. (2023) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt56998.2023.10307957 · Cited by 6
Rabby, G., D’Souza, J., Oelen, A., Dvořáčková, L., Svátek, V., & Auer, S. (2023) · Journal of Biomedical Semantics · doi:10.1186/s13326-023-00298-4 · Cited by 6
-generAItor: Tree-in-the-loop Text Generation for Language Model Explainability and Adaptation
Spinner, T., Kehlbeck, R., Sevastjanova, R., Stähle, T., Keim, D. A., Deußen, O., & El‐Assady, M. (2024) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3652028 · Cited by 11
Constraint satisfaction in large language models
Jacobs, C. L., & MacDonald, M. C. (2024) · Language Cognition and Neuroscience · doi:10.1080/23273798.2024.2364339 · Cited by 5
Dvořáčková, L. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11231-4 · Cited by 6
Cheng, K., Tang, W., Tan, L., Li, X., & Yang, J. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3575279 · Cited by 5
How Large Language Models Transform Urban Planning and Shape Tomorrow’s Cities?
Agrawal, K., & Göktaş, P. (2025) · The Springer series in applied machine learning · doi:10.1007/978-3-031-86039-3_8 · Cited by 5
Mukherjee, A., Giri, D., & Rajan, K. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00612 · Cited by 5
Bowker, L. (2022) · Terminology and lexicography research and practice · doi:10.1075/tlrp.23.06bow · Cited by 7
Representing affect information in word embeddings
Zhang, Y., Chen, W., Zhang, R., & Zhang, X. (2023) · Experiments in Linguistic Meaning · doi:10.3765/elm.2.5391 · Cited by 5
An effective negative sampling approach for contrastive learning of sentence embedding
Tan, Q., Song, X., Ye, G., & Wu, C. (2023) · Machine Learning · doi:10.1007/s10994-023-06408-8 · Cited by 5
BERT Has More to Offer: BERT Layers Combination Yields Better Sentence Embeddings
Hosseini, M., Munia, M. S., & Khan, L. R. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.1030 · Cited by 6
Foundation models in molecular biology
Si, Y., Zou, J., Gao, Y., Chuai, G., Liu, Q., & Chen, L. (2024) · Biophysics Reports · doi:10.52601/bpr.2024.240006 · Cited by 6
Academic expert finding using BERT pre-trained language model
Mannix, I. A., & Yulianti, E. (2024) · International Journal of Advances in Intelligent Informatics · doi:10.26555/ijain.v10i2.1497 · Cited by 9
The Generative Generic-Field Design Method Based on Design Cognition and Knowledge Reasoning
Mo, Z., Gong, L., Zhu, M., & Lan, J. (2024) · Sustainability · doi:10.3390/su16229841 · Cited by 5
Quantifying the Contextualization of Word Representations with Semantic Class Probing
Zhao, M., Dufter, P., Yaghoobzadeh, Y., & Schütze, H. (2020) · Open access LMU (Ludwid Maxmilian's Universitat Munchen) · doi:10.5282/ubm/epub.74039 · Cited by 5
Learning word representation by jointly using neighbor and syntactic contexts
Tian, C., Rong, W., Zhou, S., Zhang, J., Ouyang, Y., & Xiong, Z. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.03.130 · Cited by 5
Modelling General Properties of Nouns by Selectively Averaging Contextualised Embeddings
Li, N., Bouraoui, Z., Camacho-Collados, J., Espinosa-Anke, L., Gu, Q., & Schockaert, S. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/530 · Cited by 6
Detecting Source Contextual Barriers for Understanding Neural Machine Translation
Li, G., Liu, L., Zhu, C., Wang, R., Zhao, T., & Shi, S. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3085119 · Cited by 5
Beyond the Benchmarks: Toward Human-Like Lexical Representations
Stevenson, S., & Merlo, P. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.796741 · Cited by 6
Marshman, E. (2022) · Terminology and lexicography research and practice · doi:10.1075/tlrp.23.13mar · Cited by 5
Investigating perception of spoken dialogue acceptability through surprisal
Wallbridge, S., Lai, C., & Bell, P. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10808 · Cited by 5
Pavlova, V., & Makhlouf, M. (2023) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2023.bionlp-1.31 · Cited by 5
Integrating Knowledge Graph Embeddings and Pre-trained Language Models in Hypercomplex Spaces
Nayyeri, M., Wang, Z., Akter, M. M., Alam, M. M., Rony, M. R. A. H., Lehmann, J., & Staab, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47240-4_21 · Cited by 5
Improving Contextual Representation with Gloss Regularized Pre-training
Yu, L., An, Z., Wu, P., & Ma, Z. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.68 · Cited by 5
Abstractive Text Summarization Using Hybrid Technique of Summarization
Liaqat, M. I., Hamid, I., Nawaz, Q., & Shafique, N. (2022) · IEEE International Conference on Communication Software and Networks · doi:10.1109/iccsn55126.2022.9817599 · Cited by 5
ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery
Ng, K. W., Zhu, X., Song, Y.-Z., & Xiang, T. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00128 · Cited by 4
Clinical entity-aware domain adaptation in low resource setting for inflammatory bowel disease
Francis, S., Garcia, F. C., Kanimozhi, U., Mestdagh, W., Moor, B. D., & Moens, M. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1450477 · Cited by 4
Exploring Religions and Cross-Cultural Sensitivities in Conversational AI
Shuvo, M. R., Debnath, R., Hasan, N., Nazara, R., Rahman, F. N., Riad, M. J. A., & Roy, P. (2025) · International Conference on Artificial Intelligence and Data Engineering (AIDE) · doi:10.1109/aide64228.2025.10987489 · Cited by 4
Arkangel AI: A conversational agent for real-time, evidence-based medical question-answering
Villa, M. C., Castano-Villegas, N., Llano, I., Martinez, J., Guevara, M. F., Zea, J., & Velásquez, L. (2025) · Intelligence-Based Medicine · doi:10.1016/j.ibmed.2025.100274 · Cited by 4
Kim, M. K., Kim, Y., Kang, H. J., Seo, H., Choi, H., Han, J., Kee, G., Ko, S., Jung, H., Kim, B., et al. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03145-x · Cited by 4
Contrastive learning with hard negatives for sentence embeddings
Liu, W., Yang, Z., Li, C., Hong, Z., Ma, J., Liu, Z., Zhang, L., & Huang, F. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113685 · Cited by 4
Mischler, G., Li, Y. A., Bickel, S., Mehta, A. D., & Mesgarani, N. (2025) · Nature Communications · doi:10.1038/s41467-025-63961-7 · Cited by 5
Revisiting Word Embeddings in the LLM Era
Mahajan, Y., Freestone, M., Bansal, N., Aakur, S. N., & Karmaker, S. (2025) · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · doi:10.18653/v1/2025.ijcnlp-long.145 · Cited by 4
AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese
Nath, A., Mannan, S., & Krishnaswamy, N. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.739 · Cited by 4
COMBO: A Complete Benchmark for Open KG Canonicalization
Jiang, C., Jiang, Y., Wu, W., Zheng, Y., Xie, P., & Tu, K. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.26 · Cited by 4
Brglez, M. (2023) · Workshop on Slavic Natural Language Processing (SlavicNLP) · doi:10.18653/v1/2023.bsnlp-1.8 · Cited by 4
Nikolaev, D., & Padó, S. (2023) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2023.blackboxnlp-1.11 · Cited by 7
Petersen, M., & van der Plas, L. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.1022 · Cited by 4
Beck, C., & Köllner, M. (2023) · Workshop on Computational Approaches to Historical Language Change (LChange) · doi:10.18653/v1/2023.lchange-1.4 · Cited by 4
Frequency Balanced Datasets Lead to Better Language Models
Zevallos, R., Farrús, M., & Bel, N. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.527 · Cited by 4
Role of Artificial Intelligence in Improving Syncope Management
Thiruganasambandamoorthy, V., Probst, M. A., Poterucha, T. J., Sandhu, R. K., Toarta, C., Raj, S. R., Sheldon, R. S., Rahgozar, A., & Grant, L. (2024) · Canadian Journal of Cardiology · doi:10.1016/j.cjca.2024.05.027 · Cited by 4
Studying word meaning evolution through incremental semantic shift detection
Periti, F., Picascia, S., Montanelli, S., Ferrara, A., & Tahmasebi, N. (2024) · Language Resources and Evaluation · doi:10.1007/s10579-024-09769-1 · Cited by 4
Lee, M. (2024) · Fractal and Fractional · doi:10.3390/fractalfract8100552 · Cited by 5
Hybrid contrastive multi-scenario learning for multi-task sequential-dependence recommendation
Yi, Q., Wu, L., Tang, J., Zeng, Y., & Song, Z. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106953 · Cited by 4
Huang, Y., Zhu, S., Liu, W., Wang, J., & Wei, X. (2025) · Symmetry · doi:10.3390/sym17050646 · Cited by 4
Optimizing SMS Spam Detection with Large Language Models and Transformer Architectures
Ahmed, M. H., Ahamed, A. S. M. S., & Tamim, F. S. (2025) · International Conference on Electrical, Computer and Communication Engineering · doi:10.1109/ecce64574.2025.11013998 · Cited by 4
Wang, Z., Dong, C., & Shang, J. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.453 · Cited by 4
Srivastava, V. P., Pilli, S., Bhat, S., Pedanekar, N., & Karande, S. S. (2021) · Workshop on Knowledge Extraction and Integration for Deep Learning Architectures: Deep Learning Inside Out (DeeLIO) · doi:10.18653/v1/2021.deelio-1.12 · Cited by 4
Pecman, M., & Kübler, N. (2022) · Terminology and lexicography research and practice · doi:10.1075/tlrp.23.12pec · Cited by 8
Benefits from Variational Regularization in Language Models
Ferner, C., & Wegenkittl, S. (2022) · Machine Learning and Knowledge Extraction · doi:10.3390/make4020025 · Cited by 5
Kageura, K. (2022) · Terminology and lexicography research and practice · doi:10.1075/tlrp.23.21kag · Cited by 5
Adapting Static and Contextual Representations for Policy Gradient-Based Summarization
Lin, C.-S., Jwo, J., & Lee, C. (2023) · Sensors · doi:10.3390/s23094513 · Cited by 4
On the Transformation of Latent Space in Fine-Tuned NLP Models
Durrani, N., Sajjad, H., Dalvi, F., & Alam, F. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.97 · Cited by 10
Exploring Semantic Word Representations for Recognition-Free NLP on Handwritten Document Images
Tüselmann, O., & Fink, G. A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-41685-9_6 · Cited by 4
GAP-Gen: Guided Automatic Python Code Generation
Zhao, J., Song, Y., Wang, J., & Harris, I. G. (2023) · Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop (EACL SRW) · doi:10.18653/v1/2023.eacl-srw.4 · Cited by 6
Text Rendering Strategies for Pixel Language Models
Lotz, J. F., Salesky, E., Rust, P., & Elliott, D. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.628 · Cited by 7
Li, F., Su, P., Duan, J., & Xiao, W. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.635 · Cited by 4
Submodular Span, with Applications to Conditional Data Summarization
Kumari, L., & Bilmes, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i14.17465 · Cited by 4
Exploring Sentence Embedding Structures for Semantic Relation Extraction
Kalinowski, A., & An, Y. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534215 · Cited by 4
A Prior Probability of Speaker Information and Emojis Embedding Approach to Sarcasm Detection
Wang, Y., Xu-yang, X., Gao, Z., & Shi, X. (2021) · IEEE International Conference on Teaching, Assessment, and Learning for Engineering · doi:10.1109/tale52509.2021.9678900 · Cited by 4
Dury, P. (2022) · Terminology and lexicography research and practice · doi:10.1075/tlrp.23.19dur · Cited by 8
From BERT‘s Point of View: Revealing the Prevailing Contextual Differences
Schuster, C. M., & Hegelich, S. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.89 · Cited by 5
What do Toothbrushes do in the Kitchen? How Transformers Think our World is Structured
Henlein, A., & Mehler, A. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.425 · Cited by 7
A BERT-Based Scoring System for Workplace Safety Courses in Italian
Arici, N., Gerevini, A., Putelli, L., Serina, I., & Sigalini, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-27181-6_32 · Cited by 4
Isotropic Representation Can Improve Dense Retrieval
Jung, E., Park, J., Choi, J., Kim, S., & Rhee, W. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-33380-4_10 · Cited by 6
Xie, J., Su, Q., Zhang, S., & Zhang, X. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.617 · Cited by 4
Masked Latent Semantic Modeling: an Efficient Pre-training Alternative to Masked Language Modeling
Berend, G. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.876 · Cited by 5
Qiu, Z., Su, Q., Yu, J., & Si, S. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.54 · Cited by 4
Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding TransformationPreprint
Xu, H., & Koehn, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02212 · Cited by 4
VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models
Wolfe, R., & Caliskan, A. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21400 · Cited by 5
An Efficient Corpus Indexer for dynamic corpora retrieval
Zou, A., Hao, W., Jin, D., Zou, S., Zheng, Y., Sun, F., & Li, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124306 · Cited by 3
Robust Sequence-Based Self-Supervised Representation Learning for Anti-Money Laundering
Huang, S., Xiong, Y., Xie, Y., Qiu, T., & Wang, G. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3680078 · Cited by 3
Neural text embeddings in psychological research: A guide with examples in R.
Teitelbaum, L., & Simchon, A. (2025) · Psychological Methods · doi:10.1037/met0000768 · Cited by 4
Yang, B., Xie, S., & Li, L. (2025) · Systems · doi:10.3390/systems13090728 · Cited by 3
Yu, Z., Yang, D., Chen, Q., Zhang, Y., Li, Z., Wang, Y., Wang, C., & Zhang, Y. (2026) · Cell Genomics · doi:10.1016/j.xgen.2025.101130 · Cited by 4
An, Y., Hou, N., & Lv, Z. (2026) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70084 · Cited by 3
Wright, S. E. (2022) · Terminology and lexicography research and practice · doi:10.1075/tlrp.23.04wri · Cited by 3
Concept management for Terminology
Meyer, I. (2022) · Terminology and lexicography research and practice · doi:10.1075/tlrp.23.05mey · Cited by 3
Units of understanding in Sociocognitive Terminology studies
Temmerman, R. (2022) · Terminology and lexicography research and practice · doi:10.1075/tlrp.23.15tem · Cited by 4
Unbalanced Optimal Transport for Unbalanced Word Alignment
Arase, Y., Bao, H., & Yokoi, S. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.219 · Cited by 3
Grouped Contrastive Learning of Self-Supervised Sentence Representation
Wang, Q., Zhang, W., Lei, T., & Peng, D. (2023) · Applied Sciences · doi:10.3390/app13179873 · Cited by 4
Impact of Effective Word Vectors on Deep Learning Based Subjective Classification of Online Reviews
Priya Kamath, B., Geetha, M. K., Acharya, U. D., Nandi, R., & Urolagin, S. (2024) · Journal of Machine and Computing · doi:10.53759/7669/jmc202404069 · Cited by 3
An Exploration Into the Mechanisms and Evolution of GPT Models
AlShannaq, F. B., Shehab, M., Assaf, A. H. A., Alhenawi, E., & Awawdeh, S. (2024) · Advances in educational technologies and instructional design book series · doi:10.4018/979-8-3693-0884-4.ch018 · Cited by 3
A multi-label text classifier: application on an Italian public tender procedure, project ISCOL@
Locatelli, M., Tagliabue, L. C., & Giuda, G. M. D. (2024) · Journal of Information Technology in Construction · doi:10.36680/j.itcon.2024.038 · Cited by 3
A generative approach to extrapolate word concreteness ratings
Wang, T., & Xu, X. (2025) · Quarterly Journal of Experimental Psychology · doi:10.1177/17470218251320641 · Cited by 3
Metadata
- 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
- 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
