Bin Liang
Skip Abstract Section
Abstract
Existing aspect-based/category sentiment analysis methods have shown great success in detecting sentiment polarity toward a given aspect in a sentence with supervised learning, where the training and inference stages share the same pre-defined set of aspects. However, in practice, the aspect categories are changing rather than keeping fixed over time. Dealing with unseen aspect categories is under-explored in existing methods. In this article, we formulate a new few-shot aspect category sentiment analysis (FSACSA) task, which aims to effectively predict the sentiment polarity of previously unseen aspect categories. To this end, we propose a novel Aspect-Focused Meta-Learning (AFML) framework that constructs aspect-aware and aspect-contrastive representations from external knowledge to match the target aspect with aspects in the training set. Concretely, we first construct two auxiliary contrastive sentences for a given sentence with the incorporation of external knowledge, enabling the learning of sentence representations with a better generalization. Then, we devise an aspect-focused induction network to leverage the contextual sentiment toward a given aspect to refine the label vectors. Furthermore, we employ the episode-based meta-learning algorithm to train the whole network, so as to learn to generalize to novel aspects. Extensive experiments on multiple real-life datasets show that our proposed AFML framework achieves the state-of-the-art results for the FSACSA task.
- [1] . 2020. Zero-shot stance detection: A dataset and model using generalized topic representations. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 8913–8931.Google Scholar
Cross Ref
- [2] . 2021. Adversarial learning for zero-shot stance detection on social media. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 4756–4767.
DOI: Google ScholarCross Ref - [3] . 2020. Learning to few-shot learn across diverse natural language classification tasks. In Proceedings of the 28th International Conference on Computational Linguistics. 5108–5123.Google ScholarCross Ref
- [4] . 2020. Self-supervised meta-learning for few-shot natural language classification tasks. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 522–534.Google ScholarCross Ref
- [5] . 2020. Few-shot text classification with distributional signatures. In Proceedings of the International Conference on Learning Representations.Google Scholar
- [6] . 2020. Few-shot learning for opinion summarization. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 4119–4135.Google ScholarCross Ref
- [7] . 2020. Aspect-category based sentiment analysis with hierarchical graph convolutional network. In Proceedings of the 28th International Conference on Computational Linguistics. 833–843.Google ScholarCross Ref
- [8] . 2020. SenticNet 6: Ensemble application of symbolic and subsymbolic AI for sentiment analysis. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management. 105–114.Google ScholarDigital Library
- [9] . 2018. SenticNet 5: Discovering conceptual primitives for sentiment analysis by means of context embeddings. In Proceedings of the Annual AAAI Conference on Artificial Intelligence (AAAI’18). 1795–1802.Google ScholarCross Ref
- [10] . 2020. A simple framework for contrastive learning of visual representations. In Proceedings of the International Conference on Machine Learning. PMLR, 1597–1607.Google Scholar
- [11] . 2020. A multi-task incremental learning framework with category name embedding for aspect-category sentiment analysis. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 6955–6965.Google ScholarCross Ref
- [12] . 2020. Meta-learning with dynamic-memory-based prototypical network for few-shot event detection. In Proceedings of the 13th International Conference on Web Search and Data Mining. 151–159.Google ScholarDigital Library
- [13] . 2020. When low resource NLP meets unsupervised language model: Meta-pretraining then meta-learning for few-shot text classification (student abstract). In Proceedings of the Annual AAAI Conference on Artificial Intelligence (AAAI’20). 13773–13774.Google ScholarCross Ref
- [14] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171–4186.Google Scholar
- [15] . 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the 34th International Conference on Machine Learning-Volume 70. 1126–1135.Google ScholarDigital Library
- [16] . 2005. Pulse: Mining customer opinions from free text. In Proceedings of the International Symposium on Intelligent Data Analysis. Springer, 121–132.Google ScholarDigital Library
- [17] . 2019. Hybrid attention-based prototypical networks for noisy few-shot relation classification. In Proceedings of the Annual AAAI Conference on Artificial Intelligence, Vol. 33. 6407–6414.Google ScholarDigital Library
- [18] . 2019. Induction networks for few-shot text classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 3895–3904.Google ScholarCross Ref
- [19] . 2019. Attentive aspect modeling for review-aware recommendation. ACM Trans. Inf. Syst. 37, 3, Article
28 (March 2019), 27 pages.DOI: Google ScholarDigital Library - [20] . 2018. FewRel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 4803–4809.Google ScholarCross Ref
- [21] . 2020. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20). IEEE, 9726–9735.
DOI: Google ScholarCross Ref - [22] . 2011. Transforming auto-encoders. In Proceedings of the International Conference on Artificial Neural Networks. Springer, 44–51.Google ScholarCross Ref
- [23] . 1997. Long short-term memory. Neur. Comput. 9, 8 (1997), 1735–1780.Google ScholarDigital Library
- [24] . 2004. Mining and summarizing customer reviews. In Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 168–177.Google ScholarDigital Library
- [25] . 2021. Multi-label few-shot learning for aspect category detection. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, 6330–6340.
DOI: Google ScholarCross Ref - [26] . 2020. Weakly-supervised aspect-based sentiment analysis via joint aspect-sentiment topic embedding. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). Association for Computational Linguistics, 6989–6999.
DOI: Google ScholarCross Ref - [27] . 2019. A challenge dataset and effective models for aspect-based sentiment analysis. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 6280–6285.Google ScholarCross Ref
- [28] . 2014. NRC-canada-2014: Detecting aspects and sentiment in customer reviews. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval’14). 437–442.Google ScholarCross Ref
- [29] . 2015. Siamese neural networks for one-shot image recognition. In Proceedings of the ICML Deep Learning Workshop, Vol. 2. Lille.Google Scholar
- [30] . 2020. Extensively matching for few-shot learning event detection. In Proceedings of the 1st Joint Workshop on Narrative Understanding, Storylines, and Events. 38–45.Google ScholarCross Ref
- [31] . 2011. One shot learning of simple visual concepts. In Proceedings of the Annual Meeting of the Cognitive Science Society, Vol. 33.Google Scholar
- [32] . 2015. A set of complexity measures designed for applying meta-learning to instance selection. IEEE Trans. Knowl. Data Eng. 27, 2 (2015), 354–367.
DOI: Google ScholarCross Ref - [33] . 2020. Few-shot named entity recognition via meta-learning. IEEE Trans. Knowl. Data Eng. (2020), 1–1.
DOI: Google ScholarCross Ref - [34] . 2020. Multi-instance multi-label learning networks for aspect-category sentiment analysis. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 3550–3560.Google ScholarCross Ref
- [35] . 2021. Embedding refinement framework for targeted aspect-based sentiment analysis. IEEE Trans. Affect. Comput. (2021), 1–1.
DOI: Google ScholarCross Ref - [36] . 2020. Aspect-invariant sentiment features learning: Adversarial multi-task learning for aspect-based sentiment analysis. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management. 825–834.Google ScholarDigital Library
- [37] . 2021. Multilingual review-aware deep recommender system via aspect-based sentiment analysis. ACM Trans. Inf. Syst. 39, 2, Article
15 (January 2021), 33 pages.DOI: Google ScholarDigital Library - [38] . 2021. Enhancing zero-shot and few-shot stance detection with commonsense knowledge graph. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 3152–3157.Google Scholar
- [39] . 2019. Zero-shot entity linking by reading entity descriptions. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 3449–3460.Google ScholarCross Ref
- [40] . 2020. Meta-learning on heterogeneous information networks for cold-start recommendation. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1563–1573.Google ScholarDigital Library
- [41] . 2016. Label embedding for zero-shot fine-grained named entity typing. In Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers (COLING’16). 171–180.Google Scholar
- [42] . 2018. Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM. In Proceedings of the 32nd Conference on Artificial Intelligence (AAAI’18). 5876–5883.Google ScholarCross Ref
- [43] . 2000. Learning from one example through shared densities on transforms. In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR’00), Vol. 1. IEEE, 464–471.Google ScholarCross Ref
- [44] . 1995. WordNet: A lexical database for English. Commun. ACM 38, 11 (1995), 39–41.Google ScholarDigital Library
- [45] . 2017. Meta networks. In Proceedings of the International Conference on Machine Learning. PMLR, 2554–2563.Google Scholar
- [46] . 2018. On first-order meta-learning algorithms. arXiv:1803.02999. Retrieved from https://arxiv.org/abs/1803.02999.Google Scholar
- [47] . 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 1532–1543.Google ScholarCross Ref
- [48] . 2016. SemEval-2016 Task 5: Aspect based sentiment analysis. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval’16). 19–30.Google ScholarCross Ref
- [49] . 2015. SemEval-2015 Task 12: Aspect based sentiment analysis. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval’15). 486–495.Google ScholarCross Ref
- [50] . 2015. SemEval-2015 Task 12: Aspect based sentiment analysis. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval’15). 486–495.Google ScholarCross Ref
- [51] . 2014. SemEval-2014 Task 4: Aspect based sentiment analysis. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval’14). 27–35.Google ScholarCross Ref
- [52] . 2007. Extracting product features and opinions from reviews. In Natural Language Processing and Text Mining. Springer, 9–28.Google ScholarCross Ref
- [53] . 2017. Optimization as a model for few-shot learning. In Proceedings of the International Conference on Learning Representations.Google Scholar
- [54] . 2016. Meta-learning with memory-augmented neural networks. In Proceedings of the International Conference on Machine Learning. 1842–1850.Google Scholar
- [55] . 2018. Few-shot learning with graph neural networks. In Proceedings of the International Conference on Learning Representations.Google Scholar
- [56] . 2017. Supervised and unsupervised aspect category detection for sentiment analysis with co-occurrence data. IEEE Trans. Cybernet. 48, 4 (2017), 1263–1275.Google ScholarCross Ref
- [57] . 2019. Robust zero-shot cross-domain slot filling with example values. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 5484–5490.Google ScholarCross Ref
- [58] . 2017. Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems. 4077–4087.Google Scholar
- [59] . 2017. ConceptNet 5.5: An Open Multilingual Graph of General Knowledge.Google Scholar
- [60] . 2021. Knowledge guided metric learning for few-shot text classification. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 3266–3271.Google Scholar
- [61] . 2019. Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 380–385.Google Scholar
- [62] . 2018. Learning to compare: Relation network for few-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1199–1208.Google ScholarCross Ref
- [63] . 2018. Learning to attend via word-aspect associative fusion for aspect-based sentiment analysis. In Proceedings of the Annual AAAI Conference on Artificial Intelligence, Vol. 32. 5956–5963.Google ScholarCross Ref
- [64] . 1996. Is learning the n-th thing any easier than learning the first? In Advances in Neural Information Processing Systems. 640–646.Google Scholar
- [65] . 1998. Lifelong learning algorithms. In Learning to Learn. Springer, Berlin, 181–209.Google ScholarCross Ref
- [66] . 2002. A perspective view and survey of meta-learning. Artif. Intell. Rev. 18, 2 (2002), 77–95.Google ScholarDigital Library
- [67] . 2016. Matching networks for one shot learning. Adv. Neur. Inf. Process. Syst. 29 (2016), 3630–3638.Google Scholar
- [68] . 2016. Attention-based LSTM for aspect-level sentiment classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 606–615.Google ScholarCross Ref
- [69] . 2019. Aspect-level sentiment analysis using AS-capsules. In Proceedings of the World Wide Web Conference. 2033–2044.Google ScholarDigital Library
- [70] . 2020. Generalizing from a few examples: A survey on few-shot learning. ACM Comput. Surv. 53, 3 (2020), 1–34.Google ScholarDigital Library
- [71] . 2018. Meta-learning: Learning to Learn Fast. Retrieved from http://lilianweng.github.io/lil-log/2018/11/29/meta-learning.html.Google Scholar
- [72] . 2020. Scalable zero-shot entity linking with dense entity retrieval. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 6397–6407.Google ScholarCross Ref
- [73] . 2018. Aspect based sentiment analysis with gated convolutional networks. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. 2514–2523.Google ScholarCross Ref
- [74] . 2020. Simple and effective few-shot named entity recognition with structured nearest neighbor learning. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). Association for Computational Linguistics, Online, 6365–6375.
DOI: Google ScholarCross Ref - [75] . 2020. Extracting the collaboration of entity and attribute: Gated interactive networks for aspect sentiment analysis. In Natural Language Processing and Chinese Computing. 802–814.Google Scholar
- [76] . 2018. Bayesian model-agnostic meta-learning. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. 7343–7353.Google ScholarDigital Library
- [77] . 2018. Diverse few-shot text classification with multiple metrics. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 1206–1215.Google ScholarCross Ref
- [78] . 2018. Diverse few-shot text classification with multiple metrics. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 1206–1215.Google ScholarCross Ref
- [79] . 2020. Enhancing cross-target stance detection with transferable semantic-emotion knowledge. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 3188–3197.Google ScholarCross Ref
Index Terms
- Few-shot Aspect Category Sentiment Analysis via Meta-learning
Recommendations
Enhancing Aspect-Based Sentiment Analysis with Supervised Contrastive Learning
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge ManagementMost existing aspect-based sentiment analysis (ABSA) research efforts are devoted to extracting the aspect-dependent sentiment features from the sentence towards the given aspect. However, it is observed that about 60% of the testing aspects in commonly ...
Aspect and sentiment unification model for online review analysis
WSDM '11: Proceedings of the fourth ACM international conference on Web search and data miningUser-generated reviews on the Web contain sentiments about detailed aspects of products and services. However, most of the reviews are plain text and thus require much effort to obtain information about relevant details. In this paper, we tackle the ...
Sentence compression for aspect-based sentiment analysis
Sentiment analysis, which addresses the computational treatment of opinion, sentiment, and subjectivity in text, has received considerable attention in recent years. In contrast to the traditional coarse-grained sentiment analysis tasks, such as ...
Comments