Abstract
LCR-Rot-hop++ is a state-of-art model for Aspect-Based Sentiment Classification. However, it is also a black-box model where the information encoded in each layer is not understood by the user. This study uses diagnostic classifiers, single layer neural networks, to evaluate the information encoded in each layer of the LCR-Rot-hop++ model. This is done by using various hypotheses designed to test for information deemed useful for sentiment analysis. We conclude that the model did not focus on identifying the aspect mentions associated with a word and the structure of the sentence. However, the model excelled in encoding information to identify which words are related to the target. Lastly, the model was able to encode to some extent information about the word sentiment and sentiments of the words related to the target.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Adi, Y., Kermany, E., Belinkov, Y., Lavi, O., Goldberg, Y.: Fine-grained analysis of sentence embeddings using auxiliary prediction tasks. In: 2017 International Conference on Learning Representations (ICLR 2017) (2016)
Barbalau, A., Cosma, A., Ionescu, R.T., Popescu, M.: A generic and model-agnostic exemplar synthetization framework for explainable AI. In: Hutter, F., Kersting, K., Lijffijt, J., Valera, I. (eds.) ECML PKDD 2020. LNCS (LNAI), vol. 12458, pp. 190–205. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67661-2_12
Belinkov, Y., Durrani, N., Dalvi, F., Sajjad, H., Glass, J.R.: What do neural machine translation models learn about morphology? In: 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017), pp. 861–872. ACL (2017)
Chawla, N., Bowyer, K., Hall, L., Kegelmeyer, W.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Chrupała, G., Alishahi, A.: Correlating neural and symbolic representations of language. In: 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), pp. 2952–2962. ACL (2019)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Hupkes, D., Zuidema, W.: Visualisation and ‘diagnostic classifiers’ reveal how recurrent and recursive neural networks process hierarchical structure (extended abstract). In: 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), pp. 5617–5621. International Joint Conferences on Artificial Intelligence Organization (2018)
Jumelet, J., Hupkes, D.: Do language models understand anything? On the ability of LSTMs to understand negative polarity items. In: 2018 EMNLP Workshop: Analyzing and Interpreting Neural Networks for NLP (BlackBox NLP 2019), pp. 222–231. ACL (2018)
Kenter, T., de Rijke, M.: Short text similarity with word embeddings. In: 24th ACM International on Conference on Information and Knowledge Management (CIKM 2015), pp. 1411–1420. ACM (2015)
Liu, B.: Sentiment Analysis: Mining Opinions, Sentiments, and Emotions, 2nd edn. Cambridge University Press (2020)
Meijer, L., Frasincar, F., Truşcă, M.M.: Explaining a neural attention model for aspect-based sentiment classification using diagnostic classification. In: 36th Annual ACM Symposium on Applied Computing (SAC 2021), pp. 821–827. ACM (2021)
More, A.: Survey of resampling techniques for improving classification performance in unbalanced datasets. arXiv preprint arXiv:1608.06048 (2016)
Pontiki, M., et al.: SemEval-2016 task 5: aspect based sentiment analysis. In: The 10th International Workshop on Semantic Evaluation (SemEval 2016), pp. 19–30. ACL (2016)
Schouten, K., Frasincar, F.: Survey on aspect-level sentiment analysis. IEEE Trans. Knowl. Data Eng. 28(3), 813–830 (2016)
Schouten, K., Frasincar, F.: Ontology-driven sentiment analysis of product and service aspects. In: Gangemi, A., et al. (eds.) ESWC 2018. LNCS, vol. 10843, pp. 608–623. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-93417-4_39
Shiliang, Z., Xia, R.: Left-center-right separated neural network for aspect-based sentiment analysis with rotatory attention. arXiv preprint arXiv:1802.00892 (2018)
Truşcǎ, M.M., Wassenberg, D., Frasincar, F., Dekker, R.: A hybrid approach for aspect-based sentiment analysis using deep contextual word embeddings and hierarchical attention. In: Bielikova, M., Mikkonen, T., Pautasso, C. (eds.) ICWE 2020. LNCS, vol. 12128, pp. 365–380. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-50578-3_25
Wallaart, O., Frasincar, F.: A hybrid approach for aspect-based sentiment analysis using a lexicalized domain ontology and attentional neural models. In: Hitzler, P., et al. (eds.) ESWC 2019. LNCS, vol. 11503, pp. 363–378. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-21348-0_24
Zhang, Z., et al.: Semantics-aware BERT for language understanding. In: 34th AAAI Conference on Artificial Intelligence (AAAI 2021), pp. 687–719. AAAI Press (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Geed, K., Frasincar, F., Truşcǎ, M.M. (2022). Explaining a Deep Neural Model with Hierarchical Attention for Aspect-Based Sentiment Classification Using Diagnostic Classifiers. In: Di Noia, T., Ko, IY., Schedl, M., Ardito, C. (eds) Web Engineering. ICWE 2022. Lecture Notes in Computer Science, vol 13362. Springer, Cham. https://doi.org/10.1007/978-3-031-09917-5_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-09917-5_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09916-8
Online ISBN: 978-3-031-09917-5
eBook Packages: Computer ScienceComputer Science (R0)