The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties
Open accessAbstract
Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing."Downstream" tasks, often based on sentence classification, are commonly used to evaluate the quality of sentence representations.The complexity of the tasks makes it however difficult to infer what kind of information is present in the representations.We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both encoders and training methods.
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?
Probes were first introduced in NLP and have since been extensively explored in the field.
“Probes were first introduced in NLP (Köhn, 2015;Gupta et al., 2015) and have since been extensively explored in the field (Conneau et al., 2018;Tenney et al., 2019;Rogers et al., 2020;Gurnee et al., 2023;Peters et al., 2018;Burns et al., 2023;Marks & Tegmark, 2024).”
From Open Problems in Mechanistic Interpretability (2025) · cites this paper as Conneau 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
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
Moses: open source toolkit for statistical machine translation
Koehn, P., Zens, R., Dyer, C., Bojar, O., Constantin, A., Herbst, E., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., et al. (2007) · Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions - ACL '07 · doi:10.3115/1557769.1557821 · Cited by 4,735
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Williams, A., Nangia, N., & Bowman, S. (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/n18-1101 · Cited by 3,342
Convolutional Sequence to Sequence Learning
Gehring, J., Auli, M., Grangier, D., Yarats, D., & Dauphin, Y. N. (2017) · arXiv · doi:10.48550/arxiv.1705.03122 · Cited by 2,850 · cited 2×
“Complementing recent evidence that convolutional architectures are on a par with recurrent ones in seq2seq tasks (Gehring et al., 2017), we find that Gated ConvNet’s overall probing task performance is comparable to that of the best LSTM architecture (although, as shown in Appendix, the LSTM has a…”
MethodResultZhu, Y., Kiros, R., Zemel, R., Salakhutdinov, R., Urtasun, R., Torralba, A., & Fidler, S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.11 · Cited by 2,264
Vinyals, O., Kaiser, L., Koo, T., Petrov, S., Sutskever, I., & Hinton, G. (2014) · arXiv · doi:10.48550/arxiv.1412.7449 · Cited by 464
Neurophysiological dynamics of phrase-structure building during sentence processing
Nelson, M. J., El Karoui, I., Giber, K., Yang, X., Cohen, L., Koopman, H., Cash, S. S., Naccache, L., Hale, J. T., Pallier, C., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1701590114 · Cited by 319
Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation
Zhou, J., Cao, Y., Wang, X., Li, P., & Xu, W. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00105 · Cited by 216
Hupkes, D., Veldhoen, S., & Zuidema, W. (2018) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11196 · Cited by 14
Flagged first, then by citations
Research works printed but not linked: 36
- Yossi Adi, Einat Kermany, Yonatan Belinkov, Ofer Lavi, and Yoav Goldberg. 2017. Fine-grained analysis of sentence embeddings using auxil- iary prediction tasks. In Proceedings of ICLR Conference Track. Toulon, France. Published online: https://openreview.net/group? id=ICLR.cc/2017/conference.
- Sanjeev Arora, Yingyu Liang, and Tengyu Ma. 2017. A simple but tough-to-beat baseline for sentence embeddings. In Proceedings of ICLR Conference Track. Toulon, France. Published online: https://openreview.net/group? id=ICLR.cc/2017/conference.
- Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hin- ton. 2016. Layer normalization. Advances in neural information processing systems (NIPS) .
- Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, Hassan Sajjad, and James Glass. 2017a. What do neural ma- chine translation models learn about morphology? In Proceedings of ACL. Vancouver, Canada, pages 861-872.
- Yonatan Belinkov, Lluís Màrquez, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, and James Glass. 2017b. Evaluating layers of representation in neural machine translation on part-of-speech and semantic tagging tasks. In Proceedings of IJCNLP. Taipei, Taiwan, pages 1-10.
- Samuel R. Bowman, Gabor Angeli, Christopher Potts, and Christopher D. Manning. 2015. A large anno- tated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.
- Kyunghyun Cho, Bart Van Merriënboer, Caglar Gul- cehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using rnn encoder-decoder for statistical machine translation. Proceedings of EMNLP .
- Ronan Collobert and Jason Weston. 2008. A unified architecture for natural language processing: Deep neural networks with multitask learning. In Pro- ceedings of the 25th International Conference on Machine learning. ACM, pages 160-167.
- Alexis Conneau, Douwe Kiela, Holger Schwenk, Loïc Barrault, and Antoine Bordes. 2017. Supervised learning of universal sentence representations from natural language inference data. In Proceedings of EMNLP. Copenhagen, Denmark, pages 670-680.
- Fahim Dalvi, Nadir Durrani, Hassan Sajjad, Yonatan Belinkov, and Stephan Vogel. 2017. Understanding and improving morphological learning in the neural machine translation decoder. In Proceedings of IJC- NLP. Taipei, Taiwan, pages 142-151.
- Yann N Dauphin, Angela Fan, Michael Auli, and David Grangier. 2017. Language modeling with gated con- volutional networks. Proceedings of the 34th Inter- national Conference on Machine Learning .
- Allan Jabri, Armand Joulin, and Laurens van der Maaten. 2016. Revisiting visual question answering baselines. In Proceedings of ECCV. Amsterdam, the Netherlands, pages 727-739.
- Àkos Kàdàr, Grzegorz Chrupała, and Afra Alishahi. 2017. Representation of linguistic form and func- tion in recurrent neural networks. Computational Linguistics 43(4):761-780.
- Ryan Kiros, Yukun Zhu, Ruslan R Salakhutdinov, Richard Zemel, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. 2015. Skip-thought vectors. In Advances in neural information processing systems. pages 3294-3302.
- Dan Klein and Christopher Manning. 2003. Accurate unlexicalized parsing. In Proceedings of ACL. Sap- poro, Japan, pages 423-430.
- Philipp Koehn. 2005. Europarl: A parallel corpus for statistical machine translation. In MT summit. vol- ume 5, pages 79-86.
- Alice Lai and Julia Hockenmaier. 2014. Illinois-LH: A denotational and distributional approach to seman- tics. In Proceedings of SemEval. Dublin, Ireland, pages 329-334.
- Jiwei Li, Xinlei Chen, Eduard Hovy, and Dan Jurafsky. 2016. Visualizing and understanding neural models in NLP. In Proceedings of NAACL. San Diego, CA, pages 681-691.
- Jiwei Li, Monroe Will, and Dan Jurafsky. 2017. Ef- ficient estimation of word representations in vec- tor space. https://arxiv.org/abs/1612. 08220.
- Tal Linzen, Emmanuel Dupoux, and Yoav Goldberg. 2016. Assessing the ability of LSTMs to learn syntax-sensitive dependencies. Transactions of the Association for Computational Linguistics 4:521- 535.
- Marco Marelli, Stefano Menini, Marco Baroni, Luisa Bentivogli, Raffaella Bernardi, and Roberto Zam- parelli. 2014. A SICK cure for the evaluation of compositional distributional semantic models. In Proceedings of LREC. Rekjavik, Iceland, pages 216-223.
- Tomas Mikolov, Edouard Grave, Piotr Bojanowski, Christian Puhrsch, and Armand Joulin. 2018. Ad- vances in pre-training distributed word representa- tions. In Proceedings of LREC. Miyazaki, Japan.
- Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. 2013. Linguistic regularities in continuous space word representations. In Proceedings of NAACL. Atlanta, Georgia, pages 746-751.
- Tasha Nagamine, Michael L. Seltzer, and Nima Mes- garani. 2015. Exploring how deep neural net- works form phonemic categories. In Proceedings of INTERSPEECH. Dresden, Germany, pages 1912- 1916.
- Bo Pang and Lillian Lee. 2004. A sentimental educa- tion: Sentiment analysis using subjectivity summa- rization based on minimum cuts. In Proceedings of ACL. Barcelona, Spain, pages 271-278.
- Denis Paperno, Germán Kruszewski, Angeliki Lazari- dou, Ngoc Quan Pham, Raffaella Bernardi, San- dro Pezzelle, Marco Baroni, Gemma Boleda, and Raquel Fernandez. 2016. The LAMBADA dataset: Word prediction requiring a broad discourse con- text. In Proceedings of ACL. Berlin, Germany, pages 1525-1534.
- Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Proceedings of EMNLP. Doha, Qatar, pages 1532-1543.
- Nghia The Pham, Germán Kruszewski, Angeliki Lazaridou, and Marco Baroni. 2015. Jointly opti- mizing word representations for lexical and senten- tial tasks with the C-PHRASE model. In Proceed- ings of ACL. Beijing, China, pages 971-981.
- Rico Sennrich. 2017. How grammatical is character- level neural machine translation? assessing MT quality with contrastive translation pairs. In Pro- ceedings of EACL (Short Papers). Valencia, Spain, pages 376-382.
- Xing Shi, Inkit Padhi, and Kevin Knight. 2016. Does string-based neural MT learn source syntax? In Proceedings of EMNLP. Austin, Texas, pages 1526- 1534.
- Richard Socher, Eric Huang, Jeffrey Pennin, Andrew Ng, and Christopher Manning. 2011. Dynamic pooling and unfolding recursive autoencoders for paraphrase detection. In Proceedings of NIPS. Granada, Spain, pages 801-809.
- Sandeep Subramanian, Adam Trischler, Yoshua Ben- gio, and Christopher J Pal. 2018. Learning gen- eral purpose distributed sentence representations via large scale multi-task learning. In International Conference on Learning Representations.
- Sainbayar Sukhbaatar, Jason Weston, Rob Fergus, et al. 2015. End-to-end memory networks. In Advances in neural information processing systems. pages 2440-2448.
- Ilya Sutskever, Oriol Vinyals, and Quoc Le. 2014. Se- quence to sequence learning with neural networks. In Proceedings of NIPS. Montreal, Canada, pages 3104-3112.
- Shuai Tang, Hailin Jin, Chen Fang, Zhaowen Wang, and Virginia R de Sa. 2017. Trimming and improv- ing skip-thought vectors. Proceedings of the 2nd Workshop on Representation Learning for NLP .
- Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempit- sky. 2017. Deep image prior. https://arxiv. org/abs/1711.10925.
Cited by
Sorted by citations
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
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
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
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
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
Open Problems in Mechanistic Interpretability
Sharkey, L., Chughtai, B., Batson, J., Lindsey, J., Wu, J., Bushnaq, L., Goldowsky-Dill, N., Heimersheim, S., Ortega, A., Bloom, J., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.16496 · Cited by 291
Locating and Editing Factual Associations in GPT
Meng, K., Bau, D., Andonian, A., & Belinkov, Y. (2022) · arXiv · doi:10.48550/arxiv.2202.05262 · Cited by 230
Syntactic Structure from Deep Learning
Linzen, T., & Baroni, M. (2021) · Annual Review of Linguistics · doi:10.1146/annurev-linguistics-032020-051035 · Cited by 202
Self-citationexBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models
Hoover, B., Strobelt, H., & Gehrmann, S. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/2020.acl-demos.22 · Cited by 151
Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
Elazar, Y., Ravfogel, S., Jacovi, A., & Goldberg, Y. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00359 · Cited by 126
Do Vision Transformers See Like Convolutional Neural Networks?
Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., & Dosovitskiy, A. (2021) · arXiv · doi:10.48550/arxiv.2108.08810 · Cited by 663
Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks
Räuker, T., Ho, A., Casper, S., & Hadfield-Menell, D. (2023) · 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml54575.2023.00039 · Cited by 122
Playing games with AIs: the limits of GPT-3 and similar large language models
Sobieszek, A., & Price, T. (2022) · Minds and Machines · doi:10.1007/s11023-022-09602-0 · Cited by 86
Anderson, A. J., Kiela, D., Binder, J. R., Fernandino, L., Humphries, C. J., Conant, L. L., Raizada, R. D. S., Grimm, S., & Lalor, E. C. (2021) · The Journal of Neuroscience · doi:10.1523/jneurosci.1152-20.2021 · Cited by 70
Equity Beyond Bias in Language Technologies for Education
Mayfield, E., Madaio, M., Prabhumoye, S., Gerritsen, D., McLaughlin, B., Dixon-Román, E., & Black, A. W. (2019) · Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications · doi:10.18653/v1/w19-4446 · Cited by 62
Merrill, W., Goldberg, Y., Schwartz, R., & Smith, N. A. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00412 · Cited by 44
“An alternate approach is probing (Adi et al., 2017; Conneau et al., 2018; Hupkes and Zuidema, 2018; Hewitt and Liang, 2019; Belinkov and Glass, 2019), which investigates how directly a model’s representations encode semantic relations by measuring if they can be easily decoded from them.”
BackgroundMachine learning to extract communication and history‐taking skills in OSCE transcripts
Jani, K. H., Jones, K. A., Jones, G. W., Amiel, J., Barron, B., & Elhadad, N. (2020) · Medical Education · doi:10.1111/medu.14347 · Cited by 39
Roles and Utilization of Attention Heads in Transformer-based Neural Language Models
Jo, J.-Y., & Myaeng, S.-H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.311 · Cited by 33
Emergent Linear Representations in World Models of Self-Supervised Sequence Models
Nanda, N., Lee, A., & Wattenberg, M. (2023) · Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/2023.blackboxnlp-1.2 · Cited by 55
Probing Pretrained Models of Source Codes
Troshin, S., & Chirkova, N. (2022) · Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/2022.blackboxnlp-1.31 · Cited by 23
A structured distributional model of sentence meaning and processing
Chersoni, E., Santus, E., Pannitto, L., Lenci, A., Blache, P., & Huang, C.-R. (2019) · Natural Language Engineering · doi:10.1017/s1351324919000214 · Cited by 19
What if This Modified That? Syntactic Interventions with Counterfactual Embeddings
Tucker, M., Qian, P., & Levy, R. (2021) · Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 · doi:10.18653/v1/2021.findings-acl.76 · Cited by 16
Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
Geiger, A., Ibeling, D., Zur, A., Chaudhary, M., Chauhan, S., Huang, J., Arora, A., Wu, Z., Goodman, N., Potts, C., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.04709 · Cited by 11
Sometimes We Want Ungrammatical Translations
Parthasarathi, P., Sinha, K., Pineau, J., & Williams, A. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.275 · Cited by 9
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
Wu, Z., Arora, A., Geiger, A., Wang, Z., Huang, J., Jurafsky, D., Manning, C. D., & Potts, C. (2025) · arXiv · doi:10.48550/arxiv.2501.17148
“Past work in LM interpretability trained probes (Conneau et al., 2018; Hewitt and Manning, 2019; Belinkov et al., 2017) to measure to what extent LM representations encode properties of interest, e.g. linguistic features.”
Metadata
- Authors
- Conneau, A., Kruszewski, G., Lample, G., Barrault, L., & Baroni, M.
- Affiliations
- Le Mans Université (FR)
- Sorbonne Université (FR)
- Meta (United States) (US)
- Venue
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2018
- Pages
- 2126-2136
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2964204621
- Cited by
- 657
- References
- 9
- Citations by year
- 2026: 40 · 2025: 31 · 2024: 46 · 2023: 93 · 2022: 82 · 2021: 150 · 2020: 117 · 2019: 82 · 2018: 15
- FWCI
- 32.32
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Repositori digital de la UPF (Universitat Pompeu Fabra) (submittedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- sentence embeddings, probing tasks, linguistic features, sentence representation, sentence classification
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
