Does Syntax Need to Grow on Trees? Sources of Hierarchical Inductive Bias in Sequence-to-Sequence Networks
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Learners that are exposed to the same training data might generalize differently due to differing inductive biases. In neural network models, inductive biases could in theory arise from any aspect of the model architecture. We investigate which architectural factors affect the generalization behavior of neural sequence-to-sequence models trained on two syntactic tasks, English question formation and English tense reinflection. For both tasks, the training set is consistent with a generalization based on hierarchical structure and a generalization based on linear order. All architectural factors that we investigated qualitatively affected how models generalized, including factors with no clear connection to hierarchical structure. For example, LSTMs and GRUs displayed qualitatively different inductive biases. However, the only factor that consistently contributed a hierarchical bias across tasks was the use of a tree-structured model rather than a model with sequential recurrence, suggesting that human-like syntactic generalization requires architectural syntactic structure.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636
A unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058
Connectionism and cognitive architecture: A critical analysis
Fodor, J. A., & Pylyshyn, Z. W. (1988) · Cognition · doi:10.1016/0010-0277(88)90031-5 · Cited by 4,022
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 · cited 2×
“ure that have no clear connection to question formation, namely the recurrent unit and the type of attention; both of these aspects have been central to major advances in natural language processing (Sundermeyer et al., 2012; Bahdanau et al., 2015), so we investigate them here to see whether their contributions might…”
BackgroundThe importance of shape in early lexical learning
Landau, B., Smith, L. B., & Jones, S. S. (1988) · Cognitive Development · doi:10.1016/0885-2014(88)90014-7 · Cited by 1,174
Graves, A., Wayne, G., & Danihelka, I. (2014) · arXiv · doi:10.48550/arxiv.1410.5401 · Cited by 1,058 · cited 1×
“Implementations of attention vary in how the weights αi[j] are derived (Graves et al., 2014; Luong et al., 2015; Chorowski et al., 2015).”
BackgroundStructure Dependence in Grammar Formation
Crain, S., & Nakayama, M. (1987) · Language · doi:10.2307/415004 · Cited by 402 · cited 2×
“Though some have discussed the validity of Chomsky’s empirical claims (Crain and Nakayama, 1987; Ambridge et al., 2008; Pullum and Scholz, 2002; Legate and Yang, 2002), most of the debate has been about which mechanisms could explain the preference for MOVE-MAIN.”
BackgroundOn the Practical Computational Power of Finite Precision RNNs for Language Recognition
Weiss, G., Goldberg, Y., & Yahav, E. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p18-2117 · Cited by 226
Uncovering the Richness of the Stimulus: Structure Dependence and Indirect Statistical Evidence
Reali, F., & Christiansen, M. H. (2005) · Cognitive Science · doi:10.1207/s15516709cog0000_28 · Cited by 209
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages
Ravfogel, S., Goldberg, Y., & Linzen, T. (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/n19-1356 · Cited by 39 · cited 2×
“All sequential models, even the ones that generalized hierarchically with question formation, overwhelmingly chose AGREE-RECENT for this reinflection task (Figure 8), consistent with the results of a similar experiment done by Ravfogel et al. (2019). The ON-LSTM also preferred AGREERECENT.”
ResultSelf-citation
Cited by
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
Dissociating language and thought in large language models
Mahowald, K., Ivanova, A. A., Blank, I. A., Kanwisher, N., Tenenbaum, J. B., & Fedorenko, E. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2024.01.011 · Cited by 345
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-citationFindings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
Warstadt, A., Mueller, A., Choshen, L., Wilcox, E., Zhuang, C., Ciro, J., Mosquera, R., Paranjabe, B., Williams, A., Linzen, T., et al. (2023) · Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning · doi:10.18653/v1/2023.conll-babylm.1 · Cited by 74
Self-citationMcCoy, R. T., Smolensky, P., Linzen, T., Gao, J., & Celikyilmaz, A. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00567 · Cited by 70
“, 2021), typically relying on synthetic datasets to test models’ compositional abilities (Lake and Baroni, 2018; Kim and Linzen, 2020; McCoy et al., 2020).”
Self-citation
Metadata
- Authors
- McCoy, R. T., Frank, R., & Linzen, T.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press
- Published
- 2020-12
- Volume
- 8
- Pages
- 125-140
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W2999455489
- Cited by
- 66
- References
- 12
- FWCI
- 4.92
- 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.