本文总结了美团情感分析技术的演进和在典型业务场景中的应用,包括篇章/句子级情感分析、属性级情感分析和观点三元组分析,其中属性级情感分析工作向业界开源了迄今规模最大的基于真实场景的中文属性级情感分析数据集ASAP,该数据集相关论文《ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction》被自然语言处理顶会NAACL2021录用。在技术迭代上,紧跟预训练语言模型技术的快速发展,结合团队自研的MT-BERT模型不断迭代升级。在业务应用上,依托情感分析技术能力构建了在线实时预测服务和离线批量预测服务,截至目前情感分析服务已经为美团内部十多个业务场景提供服务。属性级情感分析已经在美团多个场景落地应用,但对于某些领域跨度较大的新场景(比如从餐饮领域到休闲娱乐领域),我们总是需要人工预定义新的属性,并进行一定数量的数据标注。预定义属性需要对每个业务都有深入的理解,在实际中,很难把每个业务的属性都预定义得非常全面,尤其是某些占比不高但具有业务特色的属性。这些成本会对属性级情感分析在新业务场景的快速落地有一定程度的影响。我们也在探索迁移学习、少样本学习、属性自动挖掘等技术在情感分析上的应用,以加速情感分析在新领域快速应用,来满足美团业务快速发展的需求。
参考文献
[1] https://github.com/Meituan-Dianping/asap.
[2] Bu J, Ren L, Zheng S, et al. ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.
[3] https://www.luge.ai/
[4] Zhang, L. , S. Wang , and B. Liu . "Deep Learning for Sentiment Analysis : A Survey." Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery (2018):e1253.
[5] Liu, Bing. "Sentiment analysis and opinion mining." Synthesis lectures on human language technologies 5.1 (2012): 1-167.
[6] Peng, Haiyun, et al. "Knowing what, how and why: A near complete solution for aspect-based sentiment analysis." In Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 34. No. 05. 2020.
[7] Zhang, Chen, et al. "A Multi-task Learning Framework for Opinion Triplet Extraction." In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings. 2020.
[9] Peng Zhou, Wei Shi, Jun Tian, Zhenyu Qi, Bingchen Li,Hongwei Hao, and Bo Xu. 2016. Attention-based bidirectional long short-term memory networks for relation classification. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 207–212.
[10] Devlin, Jacob, et al. “Bert: Pre-training of deep bidirectional transformers for language understanding.” arXiv preprint arXiv:1810.04805 (2018).
[11] 杨扬、佳昊等. 美团BERT的探索和实践.
[12] Pontiki, Maria, et al. "Semeval-2016 task 5: Aspect based sentiment analysis." International workshop on semantic evaluation. 2016.
[13] Pontiki, M. , et al. "SemEval-2014 Task 4: Aspect Based Sentiment Analysis." In Proceedings of International Workshop on Semantic Evaluation at (2014).
[14] Yequan Wang, Minlie Huang, and Li Zhao. 2016. Attention-based lstm for aspect-level sentiment classification. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 606–615.
[15] Sara Sabour, Nicholas Frosst, and Geoffrey E Hinton. 2017. Dynamic routing between capsules. In Advances in neural information processing systems, pages 3856–3866.
[16] Chi Sun, Luyao Huang, and Xipeng Qiu. 2019. Utilizing bert for aspect-based sentiment analysis via constructing auxiliary sentence. arXiv preprint arXiv:1903.09588.
[17] Qingnan Jiang, Lei Chen, Ruifeng Xu, Xiang Ao, and Min Yang. 2019. A challenge dataset and effective models for aspect-based sentiment analysis. 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), pages 6281–6286.
[18] Wu, Zhen, et al. "Grid Tagging Scheme for End-to-End Fine-grained Opinion Extraction." In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings. 2020.
[19] Liu, Yinhan, et al. "Roberta: A robustly optimized bert pretraining approach." arXiv preprint arXiv:1907.11692 (2019).
[20] Clark, Kevin, et al. "Electra: Pre-training text encoders as discriminators rather than generators." arXiv preprint arXiv:2003.10555 (2020).
[21] Timothy Dozat and Christopher D. Manning. 2017.Deep biaffine attention for neural dependency parsing. In 5th International Conference on Learning Representations, ICLR 2017.