Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Neural language models (LMs) perform well on tasks that require sensitivity to syntactic structure.Drawing on the syntactic priming paradigm from psycholinguistics, we propose a novel technique to analyze the representations that enable such success.By establishing a gradient similarity metric between structures, this technique allows us to reconstruct the organization of the LMs' syntactic representational space.We use this technique to demonstrate that LSTM LMs' representations of different types of sentences with relative clauses are organized hierarchically in a linguistically interpretable manner, suggesting that the LMs track abstract properties of the sentence.
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
Representational similarity analysis-connecting the branches of systems neuroscience
Kriegeskorte, N. (2008) · Frontiers in Systems Neuroscience · doi:10.3389/neuro.06.004.2008 · Cited by 3,355
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
Perez, L., & Wang, J. (2017) · arXiv · doi:10.48550/arxiv.1712.04621 · Cited by 2,499
Syntactic persistence in language production
Bock, J. K. (1986) · Cognitive Psychology · doi:10.1016/0010-0285(86)90004-6 · Cited by 1,911 · cited 1×
“This paper expands the toolkit of neural network analysis techniques by drawing on the syntactic priming paradigm, a central tool in psycholinguistics for analyzing human syntactic representations (Bock, 1986).”
MethodA probabilistic earley parser as a psycholinguistic model
Hale, J. (2001) · Second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies 2001 - NAACL '01 · doi:10.3115/1073336.1073357 · Cited by 1,150
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 · cited 2×
“Future work can explore how to bias these models to track linguistically useful properties through architectural biases (Dyer et al., 2016), training on auxiliary tasks (Enguehard et al.”
BackgroundTargeted Syntactic Evaluation of Language Models
Marvin, R., & Linzen, T. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1151 · Cited by 334 · cited 3×
“Finally, we tested the hypothesis that LMs’ accuracy on agreement prediction (Marvin and Linzen, 2018) would increase with the LMs’ ability to track more abstract properties of the sentence, but did not find evidence for this hypothesis.”
BackgroundMethodSelf-citationWhat you can cram into a single vector: Probing sentence embeddings for linguistic properties
Conneau, A., Kruszewski, G., Lample, G., Barrault, L., & Baroni, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.01070 · Cited by 263
(2019) · doi:10.18653/v1/n19-1002 · Cited by 118 · cited 2×
“…2016), visualization of individual neuron activations (Kádár et al., 2017; Qian et al., 2016), ablation of individual neurons or sets of neurons (Lakretz et al., 2019) and behavioral tests of generalization to infrequent or held out syntactic structures (Linzen et al., 2016; Weber et al.,…”
BackgroundDynamic Evaluation of Neural Sequence Models
Krause, B., Kahembwe, E., Murray, I., & Renals, S. (2017) · arXiv · doi:10.48550/arxiv.1709.07432 · Cited by 90
Cited by
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
Lack of selectivity for syntax relative to word meanings throughout the language network
Fedorenko, E., Blank, I. A., Siegelman, M., & Mineroff, Z. (2020) · Cognition · doi:10.1016/j.cognition.2020.104348 · Cited by 170
Hagendorff, T., Dasgupta, I., Binz, M., Chan, S. C. Y., Lampinen, A., Wang, J. X., Akata, Z., & Schulz, E. (2023) · arXiv · doi:10.48550/arxiv.2303.13988 · Cited by 68
(2021) · doi:10.18653/v1/2021.conll-1.15 · Cited by 51
Self-citationLampinen, A. (2024) · Computational Linguistics · doi:10.1162/coli_a_00525 · Cited by 32
“Similarly, LMs exhibit some analogous structural priming effects (Prasad, van Schijndel, and Linzen 2019; Sinclair et al. 2022), and might therefore likewise benefit from exposure to related structures before testing.”
Metadata
- Authors
- Prasad, G., van Schijndel, M., & Linzen, T.
- Venue
- Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
- Published
- 2019
- Pages
- 66-76
- OpenAlex
- W2976040964
- Cited by
- 37
- References
- 9
- FWCI
- 10.27
- 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.