Abstract
Modern neural networks specialised in natural language processing (NLP) are not implemented with any explicit rules regarding language. It has been hypothesised that they might learn something generic about language. Because of this property much research has been conducted on interpreting their inner representations. A novel approach has utilised an experimental procedure that uses human brain recordings to investigate if a mapping from brain to neural network representations can be learned. Since this novel approach has been introduced, more advanced models in NLP have been introduced. In this research we are using this novel approach to test four new NLP models to try and find the most brain aligned model. Moreover, in our effort to unravel important information on how the brain processes text semantically, we modify the text in the hope of getting a better mapping out of the models. We remove punctuation using four different scenarios to determine the effect of punctuation on semantic understanding by the human brain. Our results show that the RoBERTa model is most brain aligned. RoBERTa achieves a higher accuracy score on our evaluation than BERT. Our results also show for BERT that when punctuation was removed a higher accuracy was achieved and that as the context length increased the accuracy did not decrease as much as the original results that include punctuation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The data and the original code can be found at this link.
- 2.
References
Acunzo, D.J., Low, D.M., Fairhall, S.L.: Deep neural networks reveal topic-level representations of sentences in medial prefrontal cortex, lateral anterior temporal lobe, precuneus, and angular gyrus. Neuroimage 251, 119005 (2022). https://doi.org/10.1016/j.neuroimage.2022.119005
Beltagy, I., Lo, K., Cohan, A.: SciBERT: A Pretrained Language Model for Scientific Text. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3615–3620. Association for Computational Linguistics, Hong Kong, November 2019. https://doi.org/10.18653/v1/D19-1371
Blank, I.A., Fedorenko, E.: Domain-general brain regions do not track linguistic input as closely as language-selective regions. J. Neurosci. Official J. Soc. Neurosci. 37(41), 9999–10011 (2017). https://doi.org/10.1523/JNEUROSCI.3642-16.2017
Brennan, J., Nir, Y., Hasson, U., Malach, R., Heeger, D.J., Pylkkänen, L.: Syntactic structure building in the anterior temporal lobe during natural story listening. Brain Lang. 120(2), 163–173 (2012). https://doi.org/10.1016/j.bandl.2010.04.002
Caucheteux, C., King, J.R.: Language processing in brains and deep neural networks: computational convergence and its limits. Technical report, BioRxiv, January 2021. https://doi.org/10.1101/2020.07.03.186288. Section: New Results Type: article
Cer, D., et al.: Universal sentence encoder for English. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 169–174. Association for Computational Linguistics, Brussels, November 2018. https://doi.org/10.18653/v1/D18-2029
Chen, Y., Gilroy, S., Maletti, A., May, J., Knight, K.: Recurrent neural networks as weighted language recognizers. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 2261–2271. Association for Computational Linguistics, New Orleans, June 2018. https://doi.org/10.18653/v1/N18-1205
Chong, M., Specia, L., Mitkov, R.: Using natural language processing for automatic detection of plagiarism. In: Proceedings of the 4th International Plagiarism Conference (IPC-2010) (2010)
Clark, K., Luong, M.T., Le, Q.V., Manning, C.D.: ELECTRA: pre-training text encoders as discriminators rather than generators (2020)
Conneau, A., Kruszewski, G., Lample, G., Barrault, L., Baroni, M.: What you can cram into a single \$ &!#* vector: probing sentence embeddings for linguistic properties. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2126–2136. Association for Computational Linguistics, Melbourne, July 2018. https://doi.org/10.18653/v1/P18-1198
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. arXiv:1901.02860 [cs, stat], June 2019. arXiv: 1901.02860
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: 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), pp. 4171–4186. Association for Computational Linguistics, Minneapolis, June 2019. https://doi.org/10.18653/v1/N19-1423
Ek, A., Bernardy, J.P., Chatzikyriakidis, S.: How does punctuation affect neural models in natural language inference. In: Proceedings of the Probability and Meaning Conference (PaM 2020), pp. 109–116. Association for Computational Linguistics, Gothenburg, June 2020
Etaiwi, W., Naymat, G.: The impact of applying different preprocessing steps on review spam detection. Procedia Comput. Sci. 113, 273–279 (2017). https://doi.org/10.1016/j.procs.2017.08.368
Frank, S.L., Otten, L.J., Galli, G., Vigliocco, G.: The ERP response to the amount of information conveyed by words in sentences. Brain Lang. 140, 1–11 (2015). https://doi.org/10.1016/j.bandl.2014.10.006
Friederici, A.D.: The brain basis of language processing: from structure to function. Physiol. Rev. 91(4), 1357–1392 (2011). https://doi.org/10.1152/physrev.00006.2011
Fyshe, A., Talukdar, P.P., Murphy, B., Mitchell, T.M.: Interpretable semantic vectors from a joint model of brain- and text- based meaning. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 489–499. Association for Computational Linguistics, Baltimore, June 2014. https://doi.org/10.3115/v1/P14-1046
Hale, J., Dyer, C., Kuncoro, A., Brennan, J.R.: Finding syntax in human encephalography with beam search. arXiv:1806.04127, June 2018
Hong, W., Ji, K., Liu, J., Wang, J., Chen, J., Chu, W.: GilBERT: generative vision-language pre-training for image-text retrieval. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1379–1388. SIGIR 2021, Association for Computing Machinery, New York, July 2021. https://doi.org/10.1145/3404835.3462838
Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 328–339. Association for Computational Linguistics, Melbourne, July 2018. https://doi.org/10.18653/v1/P18-1031
Huth, A.G., de Heer, W.A., Griffiths, T.L., Theunissen, F.E., Gallant, J.L.: Natural speech reveals the semantic maps that tile human cerebral cortex. Nature 532(7600), 453–458 (2016). https://doi.org/10.1038/nature17637
Jain, S., Huth, A.G.: Incorporating context into language encoding models for fMRI. Technical report, BioRxiv, November 2018. https://doi.org/10.1101/327601. Section: New Results Type: Article
Jia, Q., Li, J., Zhang, Q., He, X., Zhu, J.: RMBERT: news recommendation via recurrent reasoning memory network over BERT. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1773–1777. SIGIR 2021, Association for Computing Machinery, New York, July 2021. https://doi.org/10.1145/3404835.3463234
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite bert for self-supervised learning of language representations, April 2020
Lerner, Y., Honey, C.J., Silbert, L.J., Hasson, U.: Topographic mapping of a hierarchy of temporal receptive windows using a narrated story. J. Neurosci. 31(8), 2906–2915 (2011). https://doi.org/10.1523/JNEUROSCI.3684-10.2011. publisher: Society for Neuroscience Section: Articles
Linzen, T., Dupoux, E., Goldberg, Y.: Assessing the ability of LSTMs to learn syntax-sensitive dependencies. arXiv:1611.01368, November 2016
Moore, N.: What’s the point? The role of punctuation in realising information structure in written English. Funct. Linguist. 3(1), 1–23 (2016). https://doi.org/10.1186/s40554-016-0029-x
Nishimoto, S., Vu, A.T., Naselaris, T., Benjamini, Y., Yu, B., Gallant, J.L.: Reconstructing visual experiences from brain activity evoked by natural movies. Curr. Biol. 21(19), 1641–1646 (2011). https://doi.org/10.1016/j.cub.2011.08.031
Peng, H., Schwartz, R., Thomson, S., Smith, N.A.: Rational recurrences. arXiv:1808.09357, August 2018
Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 2227–2237. Association for Computational Linguistics, New Orleans, June 2018. https://doi.org/10.18653/v1/N18-1202
Reddy, A.J., Wehbe, L.: Can fMRI reveal the representation of syntactic structure in the brain? In: Advances in Neural Information Processing Systems, vol. 34, pp. 9843–9856. Curran Associates, Inc. (2021)
Rowling, J.K.: Harry Potter and the Philosopher’s Stone, vol. 1, 1st edn. Bloomsbury Publishing, London (1997)
Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Shain, C., et al.: ‘Constituent length’ effects in fMRI do not provide evidence for abstract syntactic processing. Preprint, Neuroscience, November 2021. https://doi.org/10.1101/2021.11.12.467812
Søgaard, A.: Evaluating word embeddings with fMRI and eye-tracking. In: Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, pp. 116–121. Association for Computational Linguistics, Berlin, August 2016. https://doi.org/10.18653/v1/W16-2521
Sudre, G., et al.: Tracking neural coding of perceptual and semantic features of concrete nouns. Neuroimage 62(1), 451–463 (2012). https://doi.org/10.1016/j.neuroimage.2012.04.048
Toneva, M., Wehbe, L.: Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain). In: Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)
Wehbe, L., Murphy, B., Talukdar, P., Fyshe, A., Ramdas, A., Mitchell, T.: Simultaneously uncovering the patterns of brain regions involved in different story reading subprocesses. PLoS ONE 9(11), e112575 (2014). https://doi.org/10.1371/journal.pone.0112575
Wehbe, L., Vaswani, A., Knight, K., Mitchell, T.: Aligning context-based statistical models of language with brain activity during reading. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 233–243. Association for Computational Linguistics, Doha, October 2014. https://doi.org/10.3115/v1/D14-1030
Weiss, G., Goldberg, Y., Yahav, E.: On the practical computational power of finite precision RNNs for language recognition. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 740–745. Association for Computational Linguistics, Melbourne, July 2018. https://doi.org/10.18653/v1/P18-2117
Zhu, X., Li, T., de Melo, G.: Exploring semantic properties of sentence embeddings. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 632–637. Association for Computational Linguistics, Melbourne, July 2018. https://doi.org/10.18653/v1/P18-2100
Zhuang, L., Wayne, L., Ya, S., Jun, Z.: A robustly optimized BERT pre-training approach with post-training. In: Proceedings of the 20th Chinese National Conference on Computational Linguistics, pp. 1218–1227. Chinese Information Processing Society of China, Huhhot, August 2021
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lamprou, Z., Pollick, F., Moshfeghi, Y. (2023). Role of Punctuation in Semantic Mapping Between Brain and Transformer Models. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, vol 13811. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-25891-6_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25890-9
Online ISBN: 978-3-031-25891-6
eBook Packages: Computer ScienceComputer Science (R0)