CoChat
Sign Up
Cited by 251Topic ModelingNatural Language Processing TechniquesExplainable Artificial Intelligence (XAI)

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Information-Theoretic Probing with Minimum Description Length

Open access
Voita, Elena, Titov, Ivan·2020·Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
DOI 10.18653/v1/2020.emnlp-main.14
Open this paper in CoChat — free accountOpen PDF

Abstract

To measure how well pretrained representations encode some linguistic property, it is common to use accuracy of a probe, i.e. a classifier trained to predict the property from the representations.Despite widespread adoption of probes, differences in their accuracy fail to adequately reflect differences in representations.For example, they do not substantially favour pretrained representations over randomly initialized ones.Analogously, their accuracy can be similar when probing for genuine linguistic labels and probing for random synthetic tasks.To see reasonable differences in accuracy with respect to these random baselines, previous work had to constrain either the amount of probe training data or its model size.Instead, we propose an alternative to the standard probes, information-theoretic probing with minimum description length (MDL).With MDL probing, training a probe to predict labels is recast as teaching it to effectively transmit the data.Therefore, the measure of interest changes from probe accuracy to the description length of labels given representations.In addition to probe quality, the description length evaluates 'the amount of effort' needed to achieve the quality.This amount of effort characterizes either (i) size of a probing model, or (ii) the amount of data needed to achieve the high quality.We consider two methods for estimating MDL which can be easily implemented on top of the standard probing pipelines: variational coding and online coding.We show that these methods agree in results and are more informative and stable than the standard probes.1

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2020.emnlp-main.14

Cites

7 of 7 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Probing includes concept activation vectors, information-theoretic probing, and structural probing.

    “Probing also includes concept activation vectors (Kim et al., 2018a), information-theoretic probing (Voita & Titov, 2020), and structural probing (Hewitt & Manning, 2019).”

    From Open Problems in Mechanistic Interpretability (2025) · cites this paper as Voita & Titov, 2020

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

Flagged first, then by citations

Research works printed but not linked: 32

  1. Anthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, and James Glass. 2019. Iden- tifying and controlling important neurons in neural machine translation. In International Conference on Learning Representations, New Orleans.
  2. Yonatan Belinkov and James Glass. 2019. Analysis methods in neural language processing: A survey. Transactions of the Association for Computational Linguistics, 7:49-72. · DOI
  3. Léonard Blier and Yann Ollivier. 2018. The descrip- tion length of deep learning models. In Advances in Neural Information Processing Systems, pages 2216-2226.
  4. Ciprian Chelba, Tomas Mikolov, Mike Schuster, Qi Ge, Thorsten Brants, Phillipp Koehn, and Tony Robin- son. 2014. One billion word benchmark for mea- suring progress in statistical language modeling. In Fifteenth Annual Conference of the International Speech Communication Association.
  5. Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D. Manning. 2019. What does BERT look at? an analysis of BERT's attention. In Pro- ceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 276-286, Florence, Italy. Association for Computational Linguistics. · DOI
  6. Peter Grunwald. 2004. A tutorial introduction to the minimum description length principle. arXiv preprint math/0406077. · arXiv
  7. Kristina Gulordava, Piotr Bojanowski, Edouard Grave, Tal Linzen, and Marco Baroni. 2018. Colorless green recurrent networks dream hierarchically. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1195-1205. Associ- ation for Computational Linguistics. · DOI
  8. GE Hinton and D von Cramp. 1993. Keeping neu- ral networks simple by minimising the description length of weights. In Proceedings of COLT-93, pages 5-13.
  9. Antti Honkela and Harri Valpola. 2004. Variational learning and bits-back coding: an information- theoretic view to bayesian learning. In IEEE Trans- actions on Neural Networks, volume 15, pages 800- 810. · DOI
  10. Andrej Karpathy, Justin Johnson, and Li Fei-Fei. 2015. Visualizing and understanding recurrent networks. arXiv preprint arXiv:1506.02078. · arXiv
  11. Diederik Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Repre- sentation (ICLR 2015).
  12. Olga Kovaleva, Alexey Romanov, Anna Rogers, and Anna Rumshisky. 2019. Revealing the dark secrets of BERT. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natu- ral Language Processing (EMNLP-IJCNLP), pages 4365-4374, Hong Kong, China. Association for Computational Linguistics. · DOI
  13. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettle- moyer. 2017. End-to-end neural coreference reso- lution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 188-197, Copenhagen, Denmark. Association for Computational Linguistics. · DOI · Paper page
  14. Tal Linzen, Emmanuel Dupoux, and Yoav Goldberg. 2016. Assessing the ability of lstms to learn syntax- sensitive dependencies. Transactions of the Associa- tion for Computational Linguistics, 4:521-535.
  15. Christos Louizos, Karen Ullrich, and Max Welling. 2017. Bayesian compression for deep learning. In Advances in Neural Information Processing Systems, pages 3288-3298.
  16. David JC MacKay. 2003. Information theory, infer- ence and learning algorithms. Cambridge university press.
  17. Dmitry Molchanov, Arsenii Ashukha, and Dmitry Vetrov. 2017. Variational dropout sparsifies deep neural networks. In Proceedings of the 34th Inter- national Conference on Machine Learning.
  18. Fabio Petroni, Tim Rocktäschel, Sebastian Riedel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, and Alexander Miller. 2019. Language models as knowl- edge bases? In Proceedings of the 2019 Confer- ence on Empirical Methods in Natural Language Processing and the 9th International Joint Confer- ence on Natural Language Processing (EMNLP- IJCNLP), pages 2463-2473, Hong Kong, China. As- sociation for Computational Linguistics. · DOI · Paper page
  19. Ngoc-Quan Pham, German Kruszewski, and Gemma Boleda. 2016. Convolutional neural network lan- guage models. In Proceedings of the 2016 Con- ference on Empirical Methods in Natural Language Processing, pages 1153-1162, Austin, Texas. Asso- ciation for Computational Linguistics. · DOI
  20. Nina Poerner, Ulli Waltinger, and Hinrich Schütze. 2019. Bert is not a knowledge base (yet): Fac- tual knowledge vs. name-based reasoning in unsu- pervised qa. arXiv preprint arXiv:1911.03681. · arXiv
  21. Peng Qi and Christopher D. Manning. 2017. Arc-swift: A novel transition system for dependency parsing. In Proceedings of the 55th Annual Meeting of the As- sociation for Computational Linguistics (Volume 2: Short Papers), pages 110-117, Vancouver, Canada. Association for Computational Linguistics. · DOI
  22. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog, 1(8):9.
  23. Alessandro Raganato and Jörg Tiedemann. 2018. An analysis of encoder representations in transformer- based machine translation. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 287-297, Brussels, Belgium. Association for Com- putational Linguistics.
  24. Jorma Rissanen. 1984. Universal coding, information, prediction, and estimation. IEEE Transactions on Information theory, 30(4):629-636.
  25. Naomi Saphra and Adam Lopez. 2019. Understand- ing learning dynamics of language models with SVCCA. In 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), pages 3257-3267, Minneapolis, Minnesota. Associ- ation for Computational Linguistics. · DOI · Paper page
  26. Alon Talmor, Yanai Elazar, Yoav Goldberg, and Jonathan Berant. 2019. olmpics -on what lan- guage model pre-training captures. arXiv preprint arXiv:1912.13283. · arXiv
  27. Ke Tran, Arianna Bisazza, and Christof Monz. 2018. The importance of being recurrent for modeling hi- erarchical structure. In Proceedings of the 2018 Conference on Empirical Methods in Natural Lan- guage Processing, pages 4731-4736, Brussels, Bel- gium. Association for Computational Linguistics. · DOI
  28. Elena Voita, Rico Sennrich, and Ivan Titov. 2019a. The bottom-up evolution of representations in the trans- former: A study with machine translation and lan- guage modeling objectives. In Proceedings of the 2019 Conference on Empirical Methods in Natu- ral Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4396-4406, Hong Kong, China. Association for Computational Linguistics. · DOI
  29. Elena Voita, Pavel Serdyukov, Rico Sennrich, and Ivan Titov. 2018. Context-aware neural machine trans- lation learns anaphora resolution. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1264-1274, Melbourne, Australia. Associa- tion for Computational Linguistics. · DOI
  30. Elena Voita, David Talbot, Fedor Moiseev, Rico Sen- nrich, and Ivan Titov. 2019b. Analyzing multi-head self-attention: Specialized heads do the heavy lift- ing, the rest can be pruned. In Proceedings of the 57th Annual Meeting of the Association for Com- putational Linguistics, pages 5797-5808, Florence, Italy. Association for Computational Linguistics. · DOI · Paper page
  31. John Wieting and Douwe Kiela. 2019. No train- ing required: Exploring random encoders for sen- tence classification. In International Conference on Learning Representations.
  32. Dani Yogatama, Cyprien de Masson d'Autume, Jerome Connor, Tomas Kocisky, Mike Chrzanowski, Ling- peng Kong, Angeliki Lazaridou, Wang Ling, Lei Yu, Chris Dyer, and Phil Blunsom. 2019. Learning and evaluating general linguistic intelligence. arXiv preprint arXiv:1901.11373. · arXiv

Cited by

Sorted by citations

Metadata

Authors
Voita, E., & Titov, I.
Affiliations
University of Amsterdam (NL)
ORCID
Titov, Ivan
Venue
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Publisher
Association for Computational Linguistics
Published
2020
Pages
183-196
DOI
10.18653/v1/2020.emnlp-main.14
OpenAlex
W3013891696
Cited by
251
References
7
Citations by year
2026: 27 · 2025: 13 · 2024: 22 · 2023: 46 · 2022: 57 · 2021: 54 · 2020: 32
FWCI
15.12
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • UvA-DARE (University of Amsterdam) (submittedVersion, cc-by)
  • arXiv (Cornell University)
Funders
  • National Science Foundation
  • Nederlandse Organisatie voor Wetenschappelijk Onderzoek (639.022.518)
  • H2020 European Research Council (678254)
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
minimum description length, data efficiency

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