Analyzing Linguistic Knowledge in Sequential Model of Sentence
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Sentence modelling is a fundamental topic in computational linguistics.Recently, deep learning-based sequential models of sentence, such as recurrent neural network, have proved to be effective in dealing with the non-sequential properties of human language.However, little is known about how a recurrent neural network captures linguistic knowledge.Here we propose to correlate the neuron activation pattern of a LSTM language model with rich language features at sequential, lexical and compositional level.Qualitative visualization as well as quantitative analysis under multilingual perspective reveals the effectiveness of gate neurons and indicates that LSTM learns to allow different neurons selectively respond to linguistic knowledge at different levels.Cross-language evidence shows that the model captures different aspects of linguistic properties for different languages due to the variance of syntactic complexity.Additionally, we analyze the influence of modelling strategy on linguistic knowledge encoded implicitly in different sequential models.
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
Natural speech reveals the semantic maps that tile human cerebral cortex
Huth, A. G., de Heer, W. A., Griffiths, T. L., Theunissen, F. E., & Gallant, J. L. (2016) · Nature · doi:10.1038/nature17637 · Cited by 1,504
Predicting Human Brain Activity Associated with the Meanings of Nouns
Mitchell, T. M., Shinkareva, S. V., Carlson, A., Chang, K.-M., Malave, V. L., Mason, R. A., & Just, M. A. (2008) · Science · doi:10.1126/science.1152876 · Cited by 1,180
Visualizing and Understanding Recurrent Networks
Karpathy, A., Johnson, J., & Fei-Fei, L. (2015) · arXiv · doi:10.48550/arxiv.1506.02078 · Cited by 845 · cited 2×
“In addition to the findings in Karpathy et al. (2015), we see that some of the hidden layer neurons of the character-based language model seems to be sensitive to specific characters and character clusters, as is indicated from the visualization of the neuron activation pattern in Figure 10.”
BackgroundVinyals, O., Kaiser, L., Koo, T., Petrov, S., Sutskever, I., & Hinton, G. (2014) · arXiv · doi:10.48550/arxiv.1412.7449 · Cited by 464
Attention during natural vision warps semantic representation across the human brain
Çukur, T., Nishimoto, S., Huth, A. G., & Gallant, J. L. (2013) · Nature Neuroscience · doi:10.1038/nn.3381 · Cited by 351 · cited 1×
“certain words, inspired by the work in Cukur et al. (2013) and Huth et al.”
Method
Cited by
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
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
“Different units have been used, from word embeddings (K¨ohn, 2015; Qian et al., 2016b), through LSTM gates or states (Qian et al., 2016a), to sentence embeddings (Adi et al., 2016).”
BackgroundMethodAn 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
“Other recent studies look for hidden linguistic units that provide information on how the network works (Karpathy et al., 2015; Qian et al., 2016; Kádár et al., 2017), while another line of analysis probes the representation learned by a neural network as input to a classifier of another task…”
BackgroundRoles and Utilization of Attention Heads in Transformer-based Neural Language Models
Jo, J.-Y., & Myaeng, S.-H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.311 · Cited by 33
Metadata
- Authors
- Qian, P., Qiu, X., & Huang, X.
- Venue
- Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
- Published
- 2016
- Pages
- 826-835
- OpenAlex
- W2560864221
- Cited by
- 40
- References
- 6
- FWCI
- 3.63
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Analyzing Linguistic Knowledge in Sequential Model of Sentence. https://app.cochat.ai/papers/10.18653/v1/d16-1079
- The paper
- Qian, P., Qiu, X., & Huang, X. (2016). Analyzing Linguistic Knowledge in Sequential Model of Sentence. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/d16-1079
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.