The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
Open accessAbstract
The success of long short-term memory (LSTM) neural networks in language processing is typically attributed to their ability to capture long-distance statistical regularities. Linguistic regularities are often sensitive to syntactic structure; can such dependencies be captured by LSTMs, which do not have explicit structural representations? We begin addressing this question using number agreement in English subject-verb dependencies. We probe the architecture’s grammatical competence both using training objectives with an explicit grammatical target (number prediction, grammaticality judgments) and using language models. In the strongly supervised settings, the LSTM achieved very high overall accuracy (less than 1% errors), but errors increased when sequential and structural information conflicted. The frequency of such errors rose sharply in the language-modeling setting. We conclude that LSTMs can capture a non-trivial amount of grammatical structure given targeted supervision, but stronger architectures may be required to further reduce errors; furthermore, the language modeling signal is insufficient for capturing syntax-sensitive dependencies, and should be supplemented with more direct supervision if such dependencies need to be captured.
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.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545
ASPECTS OF THE THEORY OF SYNTAX
Chomsky, N. (1964) · doi:10.21236/ad0616323 · Cited by 13,587
Elman, J. L. (1990) · Cognitive Science · doi:10.1207/s15516709cog1402_1 · Cited by 11,212
Recurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390
A theory of lexical access in speech production
Levelt, W. J. M., Roelofs, A., & Meyer, A. S. (1999) · Behavioral and Brain Sciences · doi:10.1017/s0140525x99001776 · Cited by 5,136
Constraints on variables in syntax
Ross, J. R. (1967) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 4,102
The Behavioral and Brain Sciences
D., C. P. (1979) · The American Journal of Psychology · doi:10.2307/1421932 · Cited by 2,925
The Cambridge Grammar of the English Language
Huddleston, R., & Pullum, G. (2005) · Zeitschrift für Anglistik und Amerikanistik · doi:10.1515/zaa-2005-0209 · Cited by 2,408
Learning and development in neural networks: the importance of starting small
Elman, J. L. (1993) · Cognition · doi:10.1016/0010-0277(93)90058-4 · Cited by 1,988 · cited 2×
“Elman (1991) tested an SRN on a miniature language that simulated English relative clauses, and found that the network was only able to learn the language under highly specific circumstances (Elman, 1993), though later work has called some of his conclusions into question (Rohde and Plaut, 1999; Cartling, 2008).”
LSTM neural networks for language modeling
Sundermeyer, M., Schlüter, R., & Ney, H. (2012) · Interspeech 2012 · doi:10.21437/interspeech.2012-65 · Cited by 1,963
Distributed representations, simple recurrent networks, and grammatical structure
Elman, J. L. (1991) · Machine Learning · doi:10.1007/bf00114844 · Cited by 1,354
Caruana, R. (1998) · Cited by 1,110
One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling
Chelba, C., Mikolov, T., Schuster, M., Ge, Q., Brants, T., Koehn, P., & Robinson, T. (2013) · arXiv · doi:10.48550/arxiv.1312.3005 · Cited by 1,051
Visualizing and Understanding Recurrent Networks
Karpathy, A., Johnson, J., & Fei-Fei, L. (2015) · arXiv · doi:10.48550/arxiv.1506.02078 · Cited by 845
Exploring the Limits of Language Modeling
Józefowicz, R., Vinyals, O., Schuster, M., Shazeer, N., & Wu, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.02410 · Cited by 823
LSTM recurrent networks learn simple context-free and context-sensitive languages
Gers, F. A., & Schmidhuber, E. (2001) · IEEE Transactions on Neural Networks · doi:10.1109/72.963769 · Cited by 722
Visualizing and Understanding Neural Models in NLP
Li, J., Chen, X., Hovy, E., & Jurafsky, D. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1082 · Cited by 625
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
Kiperwasser, E., & Goldberg, Y. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00101 · Cited by 615
Self-citationBock, K., & Miller, C. A. (1991) · Cognitive Psychology · doi:10.1016/0010-0285(91)90003-7 · Cited by 529
Recurrent Neural Network Grammars
Dyer, C., Kuncoro, A., Ballesteros, M., & Smith, N. A. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1024 · Cited by 517
The Empirical Base of Linguistics: Grammaticality Judgments and Linguistic Methodology
Schütze, C. T. (2016) · Cited by 469
Making Syntax of Sense: Number Agreement in Sentence Production.
Eberhard, K. M., Cutting, J. C., & Bock, K. (2005) · Psychological Review · doi:10.1037/0033-295x.112.3.531 · Cited by 384
Learning to Transduce with Unbounded MemoryPreprint
Grefenstette, E., Hermann, K. M., Suleyman, M., & Blunsom, P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.02516 · Cited by 305
Language acquisition in the absence of explicit negative evidence: how important is starting small?
Rohde, D. L. T., & Plaut, D. C. (1999) · Cognition · doi:10.1016/s0010-0277(99)00031-1 · Cited by 274
Structures, Not Strings: Linguistics as Part of the Cognitive Sciences
Everaert, M. B. H., Huybregts, M. A. C., Chomsky, N., Berwick, R. C., & Bolhuis, J. J. (2015) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2015.09.008 · Cited by 245
A Recurrent Neural Network that Learns to Count
RODRIGUEZ, P., WILES, J., & ELMAN, J. L. (1999) · Connection Science · doi:10.1080/095400999116340 · Cited by 241
The 'no negative evidence' problem: How do children avoid constructing an overly general grammar?
Bowerman, M. F. (1988) · MPG.PuRe (Max Planck Society) · Cited by 218
A Dynamic Oracle for Arc-Eager Dependency Parsing
Goldberg, Y., & Nivre, J. (2012) · International Conference on Computational Linguistics · Cited by 209
Self-citationInferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
Joulin, A., & Mikolov, T. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.01007 · Cited by 165
Tanner, D., Nicol, J. L., & Brehm, L. E. (2014) · Journal of Memory and Language · doi:10.1016/j.jml.2014.07.003 · Cited by 164
On the interpretation of the number attraction effect: Response time evidence
Staub, A. (2008) · Journal of Memory and Language · doi:10.1016/j.jml.2008.11.002 · Cited by 164
Representation of Linguistic Form and Function in Recurrent Neural Networks
Kádár, Á., Chrupała, G., & Alishahi, A. (2017) · Computational Linguistics · doi:10.1162/coli_a_00300 · Cited by 148
Unbounded Dependency Recovery for Parser Evaluation
Rimell, L., Clark, S. C., & Steedman, M. J. (2009) · Cited by 82
Simple Recurrent Networks Learn Context-Free and Context-Sensitive Languages by Counting
Rodriguez, P. F. (2001) · Neural Computation · doi:10.1162/089976601750399326 · Cited by 81
Tree-structured composition in neural networks without tree-structured architecturesPreprint
Bowman, S. R., Manning, C. D., & Potts, C. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.04834 · Cited by 58
Evaluation of Dependency Parsers on Unbounded Dependencies
Nivre, J., Rimell, L., McDonald, R., & Gómez‐Rodríguez, C. (2010) · Cited by 53
Parser Evaluation over Local and Non-Local Deep Dependencies in a Large Corpus
Bender, E. M., Flickinger, D., Oepen, S., & Zhang, Y. (2012) · Cited by 31
On the implicit acquisition of a context-free grammar by a simple recurrent neural network
Cartling, B. G. (2007) · Neurocomputing · doi:10.1016/j.neucom.2007.05.006 · Cited by 22
Statistical Representation of Grammaticality Judgements: the Limits of N-Gram Models
Clark, A., Giorgolo, G., & Lappin, S. (2013) · Research Portal (King's College London) · Cited by 21
The Acquisition of Anaphora by Simple Recurrent Networks
Frank, R., Mathis, D. W., & Badecker, W. (2013) · Language Acquisition · doi:10.1080/10489223.2013.796950 · Cited by 19
Can recurrent neural networks learn natural language grammars?
Lawrence, S., Giles, C. L., & Fong, S. (2002) · IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks · doi:10.1109/icnn.1996.549183 · Cited by 15
Cited by
Universal Language Model Fine-tuning for Text Classification
Howard, J., & Ruder, S. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1031 · Cited by 4,100
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
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey
Min, B., Ross, H., Sulem, E., Veyseh, A. P. B., Nguyen, T. H., Sainz, O., Agirre, E., Heintz, I., & Roth, D. (2024) · ACM Computing Surveys · doi:10.1145/3605943 · Cited by 1,387
(2019) · doi:10.18653/v1/p19-1356 · Cited by 1,291
Neural Network Acceptability Judgments
Warstadt, A., Singh, A., & Bowman, S. R. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00290 · Cited by 1,215
Metadata
- Authors
- Linzen, T., Dupoux, E., & Goldberg, Y.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2016-12
- Volume
- 4
- Pages
- 521-535
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W2549835527
- Cited by
- 737
- References
- 43
- FWCI
- 58.37
- Type
- journal article
- Language
- en
- Open access
- diamond
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.