The DOI matches its Crossref record; 54 of the 57 references it cites were found in a registry or an index.
Dissecting Contextual Word Embeddings: Architecture and Representation
Open accessAbstract
Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks.However, many questions remain as to how and why these models are so effective.In this paper, we present a detailed empirical study of how the choice of neural architecture (e.g.LSTM, CNN, or self attention) influences both end task accuracy and qualitative properties of the representations that are learned.We show there is a tradeoff between speed and accuracy, but all architectures learn high quality contextual representations that outperform word embeddings for four challenging NLP tasks.Additionally, all architectures learn representations that vary with network depth, from exclusively morphological based at the word embedding layer through local syntax based in the lower contextual layers to longer range semantics such coreference at the upper layers.Together, these results suggest that unsupervised biLMs, independent of architecture, are learning much more about the structure of language than previously appreciated.
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
“Following Peters et al. (2018b); Liu et al. (2019a), we observe that the final 2-3 BERT layers provide embeddings that excel at predictive language modeling; as such, Figure 4 uses embeddings from layer 9 of S2ORC-SCIBERT.”
From S2ORC: The Semantic Scholar Open Research Corpus (2020) · cites this paper as Peters et al. (2018b)
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The study by Peters et al. (2018) suggests that the context vectors of bi-directional language models undergo abrupt changes at syntactic boundaries, allowing them to be utilized for constructing representations of spans or consecutive token sequences.”
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 Peters et al., 2018
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
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
(2008) · Journal of Machine Learning Research · Cited by 33,051
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
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
Lafferty, J., McCallum, A., & Pereira, F. C. N. (2001) · ScholarlyCommons (University of Pennsylvania) · Cited by 12,935
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
Self-citationBuilding a Large Annotated Corpus of English: The Penn Treebank
Marcus, M. (1993) · doi:10.21236/ada273556 · Cited by 7,405
ADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322
Flagged first, then by citations
3 of the 57 references couldn’t be matched to a known paper.
Research works printed but not linked: 4
- Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, Has- san Sajjad, and James R. Glass. 2017. What do neu- ral machine translation models learn about morphol- ogy? In ACL.
- Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander M. Rush. 2017. Open- NMT: Open-source toolkit for neural machine trans- lation. In ACL.
- Liyuan Liu, Xiang Ren, Jingbo Shang, Jian Peng, and Jiawei Han. 2018. Efficient contextualized represen- tation: Language model pruning for sequence label- ing. In EMNLP.
- Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word rep- resentations. In NAACL.
Cited by
Sorted by citations
Items 401–436 of 436
Disentangling the Linguistic Competence of Privacy-Preserving BERT
Arnold, S., Kemmerzell, N., & Schreiner, A. (2023) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2023.blackboxnlp-1.5
Chen, X., Li, L., Zhang, M., & Zhang, R. (2024) · Human-Centric Intelligent Systems · doi:10.1007/s44230-023-00054-y
IEEE Annals of the History of Computing
(2024) · IEEE Software · doi:10.1109/ms.2024.3375990
Transformer Hybrid Neural Network Model for Natural Language Reasoning
Jiao, B., & Huang, Y. (2024) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac59436.2024.10503713
Toward Visual Syntactical Understanding
Chowdhury, S. S., Chandra, S., & Roy, K. (2024) · IEEE Access · doi:10.1109/access.2024.3397061
Alaba, F. A., & Rocha, A. (2024) · Studies in systems, decision and control · doi:10.1007/978-3-031-65929-4_2
Nagender, Y., Ravichand, M., Kocherlakota, N., Mary, S. S. C., Bharathi, S. K., & Kalaivaani, P. C. D. (2024) · Smart innovation, systems and technologies · doi:10.1007/978-981-97-2716-2_23
SDM-M-DID: Self-decoding model for medical de-identification
Budiakov, B., Liu, T., Chen, J., & Karev, A. (2025) · Intelligent Data Analysis · doi:10.1177/1088467x251332846
Individual vs. group dynamics: Impacts on equilibrium states in self-organizing systems
Li, X., & Vargas, D. V. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130575
GISA: Gradual Information Selection Attention for MCQ Difficulty Estimation
Ravikiran, M., Sharma, T., Bhavsar, A. V., & Saluja, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98414-3_14
Chen, R., Yan, C., Zhang, H., & Zheng, S. (2024) · International Conference on Mechatronics and Computer Technology Engineering (MCTE) · doi:10.1109/mcte62870.2024.11117615
Assessing the Quality of Behavior-Driven Development Scenarios Using BERT
Alinezhadtilaki, N., & Evans, C. R. (2025) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi65310.2025.11141197
Scalable Structural Similarity Analysis of JSON documents Using MapReduce
Drissi, A., d’Orazio, L., & Damigos, M. (2025) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz62266.2025.11152080
A Comprehensive Survey on Protein Function Prediction
Shukla, V., Pradhan, R., Sharma, D. K., & Nagaty, K. A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-9242-2_35
Media portrayal and location behavior: Crime reporting and house prices in U.S. cities
Sobhani, A., Burger, M., Cardoso, R. V., & Meijers, E. J. (2026) · Journal of Urban Affairs · doi:10.1080/07352166.2025.2607394
Yıldırım, B., Alsan, H. F., & Arsan, T. (2026) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3798051
Kozyreva, A. B., Tikhomirov, I. A., Devyatkin, D. A., & Соченков, И. В. (2025) · Scientific and Technical Information Processing · doi:10.3103/s0147688225700546
Evaluating Semantic Alignment between Teacher and Student Concept Maps Using IndoBERT
Prasetya, D. D., Wiryawan, M. Z., Widiyaningtyas, T., Rismayanti, N., Zain, A. M., & Sari, H. V. (2025) · Beyond Technology Summit on Informatics International Conference (BTS-I2C) · doi:10.1109/bts-i2c67944.2025.11399388
Rongchang, G., & Peng, Y. (2026) · AIP Advances · doi:10.1063/5.0310465
Analyse d'opinion dans les interactions orales
Barriere, V. (2019) · theses.fr (ABES) · doi:10.70675/d65df106z9fe1z44f0zb9bbzb1caa1590c7a
Belkacem, T. (2019) · theses.fr (ABES) · doi:10.70675/f480bd4dz0f08z4e64z9c2fz484276575ac4
Modèles neuronaux de recommandation basés sur les folksonomies
Boudiba, T.-R. (2022) · theses.fr (ABES) · doi:10.70675/d648a3f8za16cz4ec1zb0cazcb6dae34386d
Word Meaning Representation in Neural Language Models : Lexical Polysemy and Semantic Relationships
Soler, A. G. (2021) · theses.fr (ABES) · doi:10.70675/99a10411zc05ez4135z8f31z13573e0fd4d1
Facing Data Scarcity in Dialogues for Discourse Structure Discovery and Prediction
Li, C. (2023) · theses.fr (ABES) · doi:10.70675/c379d1f5z5324z4865z9c13z84c9508836f1
Improving Representations for Language Modeling
Godey, N. (2024) · theses.fr (ABES) · doi:10.70675/b6a15d0ez15bez43e5za967z16a069e0a8bb
The Digital Turn in the Humanities
Alaba, F. A., & Ajibola, I. G. (2026) · Information systems engineering and management · doi:10.1007/978-3-032-20335-9_2
The Mechanism behind Understanding Anaphoric One and Noun Phrase Ellipsis: How Language Models Work
Kim, N., Bak, J., Duan, Y., Li, Z., Sanskriti, & Kim, K. (2026) · Computational Linguistics · doi:10.1162/coli.a.626
Feedback with BERT: When Detecting Students’ Misconceptions Becomes Automatic
Steveny, G., Lienard, J., Mens, K., & Nijssen, S. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-25305-7_38
A Representation-Level Assessment of Bias Mitigation in Foundation Models
Nizhnichenkov, S., Nair, R., Daly, E. M., & Namee, B. M. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-19096-3_13
Not all linguistic variation is equally predictable
Morger, F., & Berdičevskis, A. (2026) · International Journal of Corpus Linguistics · doi:10.1075/ijcl.24065.mor
The human language processing system straightens natural speechPreprint
Xu, J., Nguyen, T. D., Tang, J., Huth, A. G., & Goris, R. L. T. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.30.735613
Fundamentals in Management Causal DiscussionsPreprint
Wan, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7026198
Ghanadian, F., Zollanvari, A., Kural, A., & Bagheri, M. (2026) · IEEE Access · doi:10.1109/access.2026.3708777
A standardized naturalistic audio stimulus dataset with unsupervised labeling
Al-Naji, A., Schubotz, R. I., & Zahedi, A. (2026) · Scientific Data · doi:10.1038/s41597-026-08034-0
NerAxom-MGF: Leveraging Multi-Granularity Fusion for Assamese Named Entity Recognition
Sarmah, P., Lahkar, M. P., Kalita, S., & Sharma, U. (2026) · Information Retrieval Research · doi:10.54195/irrj.26376
A novel quantum-inspired phase-modulated gated recurrent unit for part-of-speech tagging
Manuel, M. L. A. E., & Raja, K. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08935-2
Metadata
- Authors
- Peters, M., Neumann, M., Zettlemoyer, L., & Yih, W.-T.
- Affiliations
- Allen Institute for Artificial Intelligence (US)
- University of Washington (US)
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 1499-1509
- OpenAlex
- W2888329843
- Cited by
- 434
- References
- 57
- Citations by year
- 2026: 23 · 2025: 27 · 2024: 37 · 2023: 53 · 2022: 55 · 2021: 75 · 2020: 83 · 2019: 77 · 2018: 4
- FWCI
- 24.08
- 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)
- 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 › Sentiment Analysis and Opinion Mining
- Keywords
- contextual word embeddings, bidirectional language models, LSTM, convolutional neural networks, self-attention, representation learning, network depth, morphological representation, syntactic representation, coreference, word embeddings, speed-accuracy trade-off
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
