Deep RNNs Encode Soft Hierarchical Syntax
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
We present a set of experiments to demonstrate that deep recurrent neural networks (RNNs) learn internal representations that capture soft hierarchical notions of syntax from highly varied supervision.We consider four syntax tasks at different depths of the parse tree; for each word, we predict its part of speech as well as the first (parent), second (grandparent) and third level (great-grandparent) constituent labels that appear above it.These predictions are made from representations produced at different depths in networks that are pretrained with one of four objectives: dependency parsing, semantic role labeling, machine translation, or language modeling.In every case, we find a correspondence between network depth and syntactic depth, suggesting that a soft syntactic hierarchy emerges.This effect is robust across all conditions, indicating that the models encode significant amounts of syntax even in the absence of an explicit syntactic training supervision.
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
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-citationEnd-to-end Neural Coreference Resolution
Lee, K., He, L., Lewis, M., & Zettlemoyer, L. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1018 · Cited by 869
Self-citationWhat 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×
“…follows Shi et al. (2016), who run syntactic feature prediction experiments over a number of different shallow machine translation models, and Belinkov et al. 2017a; 2017b, who use a similar process to study the morphological, part-of-speech, and semantic features learned by deeper machine…”
Background
Cited by
What Does BERT Look at? An Analysis of BERT’s Attention
Clark, K., Khandelwal, U., Levy, O., & Manning, C. D. (2019) · Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w19-4828 · Cited by 1,373
Self-citationBERT 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
“…evidence that deep language models can encode a range of syntactic and semantic information (e.g. Shi et al., 2016; Belinkov, 2018; Tenney et al., 2019), and that more complex structures are developed hierarchically in the higher layers of the model (Peters et al., 2018b; Blevins et al., 2018).”
BackgroundExplainability for Large Language Models: A Survey
Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cai, H., Wang, S., Yin, D., & Du, M. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3639372 · Cited by 681
“These insights have motivated the development of more robust adversarial training methods.”
BackgroundLinguistic Knowledge and Transferability of Contextual Representations
Liu, N. F., Gardner, M., Belinkov, Y., Peters, M. E., & Smith, N. A. (2019) · Proceedings of the 2019 Conference of the North · doi:10.18653/v1/n19-1112 · Cited by 621
(2019) · doi:10.18653/v1/n19-1419 · Cited by 601
Analysis Methods in Neural Language Processing: A Survey
Belinkov, Y., & Glass, J. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00254 · Cited by 477
Dissecting Contextual Word Embeddings: Architecture and Representation
Peters, M., Neumann, M., Zettlemoyer, L., & Yih, W.-T. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1179 · Cited by 434
“…et al. (2018) studied the role of context in influencing language model predictions, Gaddy et al. (2018) analyzed neural constituency parsers, Blevins et al. (2018) explored whether RNNs trained with several different objectives can learn hierarchical syntax, and Con-neau et al. (2018)…”
BackgroundSelf-citationEmergent linguistic structure in artificial neural networks trained by self-supervision
Manning, C. D., Clark, K., Hewitt, J., Khandelwal, U., & Levy, O. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1907367117 · Cited by 339
Self-citationAnalyzing the Structure of Attention in a Transformer Language Model
Vig, J., & Belinkov, Y. (2019) · Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w19-4808 · Cited by 301
“This is consistent with previous findings showing that deeper layers focus on higher-level properties (Blevins et al., 2018; Belinkov, 2018).”
BackgroundResultCompositionality Decomposed: How do Neural Networks Generalise?
Hupkes, D., Dankers, V., Mul, M., & Bruni, E. (2020) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11674 · Cited by 194
Analyzing Encoded Concepts in Transformer Language Models
Sajjad, H., Durrani, N., Dalvi, F., Alam, F., Khan, A., & Xu, J. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.225 · Cited by 24
Voita, E., Sennrich, R., & Titov, I. (2019) · arXiv · doi:10.48550/arxiv.1909.01380 · Cited by 17
Metadata
- Authors
- Blevins, T., Levy, O., & Zettlemoyer, L.
- Venue
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Published
- 2018
- Pages
- 14-19
- OpenAlex
- W2801092741
- Cited by
- 116
- References
- 3
- FWCI
- 8.53
- 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
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.