Contextual and Non-Contextual Word Embeddings: an in-depth Linguistic Investigation
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
In this paper we present a comparison between the linguistic knowledge encoded in the internal representations of a contextual Language Model (BERT) and a contextual-independent one (Word2vec).We use a wide set of probing tasks, each of which corresponds to a distinct sentence-level feature extracted from different levels of linguistic annotation.We show that, although BERT is capable of understanding the full context of each word in an input sequence, the implicit knowledge encoded in its aggregated sentence representations is still comparable to that of a contextualindependent model.We also find that BERT is able to encode sentence-level properties even within single-word embeddings, obtaining comparable or even superior results than those obtained with sentence representations.
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
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
BERT Rediscovers the Classical NLP Pipeline
Tenney, I., Das, D., & Pavlick, E. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1452 · Cited by 1,307 · cited 1×
“…et al., 2017) to more domain specific approaches, such as interpreting attention mechanisms (Raganato and Tiedemann, 2018; Kovaleva et al., 2019; Vig and Belinkov, 2019) or designing specific probing tasks that a model can solve only if it captures a precise linguistic phenomenon using the…”
Background(2019) · doi:10.18653/v1/p19-1356 · Cited by 1,291 · cited 2×
“As suggested in Jawahar et al. (2019), the [CLS] token somehow summerizes the information encoded in the input sequence.”
BackgroundVisualizing and Understanding Recurrent Networks
Karpathy, A., Johnson, J., & Fei-Fei, L. (2015) · arXiv · doi:10.48550/arxiv.1506.02078 · Cited by 845 · cited 1×
“They range from techniques to examine the activations of individual neurons (Karpathy et al., 2015; Li et al., 2016; K´ad´ar et al., 2017) to more domain specific approaches, such as interpreting attention mechanisms (Raganato and Tiedemann, 2018; Kovaleva et al., 2019; Vig and Belinkov, 2019) or…”
BackgroundEthayarajh, 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
(2019) · doi:10.18653/v1/n19-1419 · Cited by 601
Designing and Interpreting Probes with Control Tasks
Hewitt, J., & Liang, P. (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/d19-1275 · Cited by 393 · cited 1×
“…Vig and Belinkov, 2019) or designing specific probing tasks that a model can solve only if it captures a precise linguistic phenomenon using the contextual word/sentence embeddings of a pre-trained model as training features (Conneau et al., 2018; Zhang and Bowman, 2018; Hewitt and Liang, 2019).”
BackgroundAssessing BERT's Syntactic Abilities
Goldberg, Y. (2019) · arXiv · doi:10.48550/arxiv.1901.05287 · Cited by 385 · cited 1×
“Recent studies have begun to study these models in order to understand whether they encode linguistic phenomena even without being explicitly designed to learn such properties (Marvin and Linzen, 2018; Goldberg, 2019; Warstadt et al., 2019).”
Background
Cited by
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
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
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
“We also consider non-contextualized shallow embeddings [41] including TF-IDF and Word2vec [23] as a comparison.”
Background
Metadata
- Authors
- Miaschi, A., & Dell’Orletta, F.
- Venue
- Proceedings of the 5th Workshop on Representation Learning for NLP
- Published
- 2020
- Pages
- 110-119
- OpenAlex
- W3037458976
- Cited by
- 72
- References
- 14
- FWCI
- 4.03
- 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: Contextual and Non-Contextual Word Embeddings: an in-depth Linguistic Investigation. https://app.cochat.ai/papers/10.18653/v1/2020.repl4nlp-1.15
- The paper
- Miaschi, A., & Dell’Orletta, F. (2020). Contextual and Non-Contextual Word Embeddings: an in-depth Linguistic Investigation. Proceedings of the 5th Workshop on Representation Learning for NLP. https://doi.org/10.18653/v1/2020.repl4nlp-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.