The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Elena Voita, Rico Sennrich, Ivan Titov. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
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
The information bottleneck method
Tishby, N., Pereira, F. C., & Bialek, W. (2000) · arXiv · doi:10.48550/arxiv.physics/0004057 · Cited by 2,626 · cited 2×
“The IB method (Tishby et al., 1999) considers a joint distribution of input-output pairs p ( X, Y ) and aims to extract a compressed representation ˜ X for an input X such that ˜ X retains as much as possible information about the output Y .”
MethodCross-lingual Language Model Pretraining
Lample, G., & Conneau, A. (2019) · arXiv · doi:10.48550/arxiv.1901.07291 · Cited by 1,586 · cited 1×
“It is straightforward to apply the Transformer to this task (Radford et al., 2018; Lample and Conneau, 2019).”
MethodEstimation of entropy and mutual information
Paninski, L. (2003) · Neural Computation · doi:10.1162/089976603321780272 · Cited by 1,442 · cited 1×
“Even though the information-theoretic view provides insights into processes shaping the representations, direct MI estimation from finite samples for densities on multi-dimensional spaces is challenging (Paninski, 2003).”
BackgroundBERT 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 3×
“This agrees with the work by Tenney et al. (2019a).”
BackgroundResultAnalyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
Voita, E., Talbot, D., Moiseev, F., Sennrich, R., & Titov, I. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1580 · Cited by 1,146 · cited 3×
“In this work, we study how the choice of ob-jective affects the process by which information is encoded in token representations of the Trans-former (Vaswani et al., 2017), as this architecture achieves state-of-the-art results on tasks with very different objectives such as machine translation (MT) (Bojar et al., 201…”
BackgroundSelf-citationRaghu, M., Gilmer, J., Yosinski, J., & Sohl-Dickstein, J. (2017) · arXiv · doi:10.48550/arxiv.1706.05806 · Cited by 335
What do Neural Machine Translation Models Learn about Morphology?
Belinkov, Y., Durrani, N., Dalvi, F., Sajjad, H., & Glass, J. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1080 · Cited by 307 · cited 2×
“…of linguistic analysis have been considered including morphology (Belinkov et al., 2017a; Dalvi et al., 2017; Bisazza and Tump, 2018), syntax (Shi et al., 2016; Tenney et al., 2019b) and semantics (Hill et al., 2017; Belinkov et al., 2017b; Raganato and Tiedemann, 2018; Tenney et al., 2019b).”
BackgroundAn Analysis of Encoder Representations in Transformer-Based Machine Translation
Raganato, A., & Tiedemann, J. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5431 · Cited by 277 · cited 1×
“…of linguistic analysis have been considered including morphology (Belinkov et al., 2017a; Dalvi et al., 2017; Bisazza and Tump, 2018), syntax (Shi et al., 2016; Tenney et al., 2019b) and semantics (Hill et al., 2017; Belinkov et al., 2017b; Raganato and Tiedemann, 2018; Tenney et al., 2019b).”
BackgroundInsights on representational similarity in neural networks with canonical correlation
Morcos, A. S., Raghu, M., & Bengio, S. (2018) · arXiv · doi:10.48550/arxiv.1806.05759 · Cited by 171
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
Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT
Chen, Z., Chen, D., Zhang, X., Yuan, Z., & Cheng, X. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3100509 · Cited by 595
Self-supervised speech representation learning: A review
Mohamed, A., Lee, H.-Y., Borgholt, L., Havtorn, J. D., Edin, J., Igel, C., Kirchhoff, K., Li, S.-W., Livescu, K., Maaløe, L., et al. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3207050 · Cited by 372
“In an analysis of text-based Transformers trained with a masked language model criterion [269] observed a similar compression plus reconstruction pattern.”
MethodLayer-Wise Analysis of a Self-Supervised Speech Representation Model
Pasad, A., Chou, J.-C., & Livescu, K. (2021) · 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · doi:10.1109/asru51503.2021.9688093 · Cited by 262
Information-Theoretic Probing with Minimum Description Length
Voita, E., & Titov, I. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.14 · Cited by 251
Self-citation
Metadata
- Authors
- Voita, E., Sennrich, R., & Titov, I.
- 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
- 4395-4405
- OpenAlex
- W2970820321
- Cited by
- 127
- References
- 12
- FWCI
- 9.02
- Type
- conference paper
- Language
- en
- Open access
- gold
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
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.