针对金融领域文本中具有实体较多、实体长度较长以及实体间存在语义关联的特性,容易导致实体和情感极性联合获取对应错误的问题,该文提出了一种基于多图卷积网络的金融实体和情感极性联合获取方法(JAES-MGCN)。该方法利用预训练模型对句子进行初始表示,构建基于多头自注意力机制的句子权重矩阵,建立基于多个图卷积网络融合的实体边界深层语义表示。在此基础上,基于多头注意力机制,建立实体与句子之间的交互信息表示,最后在解码层实现<金融实体,情感极性>二元组联合获取。在金融实体和情感极性数据集CES-data上,与已有的模型进行对比,该文所提方法在精确率和F1值上分别提升了3.66和1.42,验证了图卷积网络有利于捕获金融实体间的语义关系,进一步在公开的英文Twitter方面项情感分析数据集上验证了该方法的有效性。
Abstract
Due to the large number of entities, long length of entities and complex semantic relationships between entities in the financial field, it is easy to lead to wrong pairs in extracted of entities and sentiment polarity. In this paper, we propose a joint acquirement method for financial entity and sentiment polarity based on multi-graph convolutional networks (JAES-MGCN). The pre-trained model is used for the initial representation of sentences, the sentence weight matrix based on multi-head self-attention mechanism is constructed, and the entity boundary representation based on the fusion of multi-graph convolutional networks is established. On this basis, interactive information representation between entities and sentences is established based on multi-head attention mechanism, and binary groups is acquired in decoding layer. Experiments demonstrate that the proposed method improves the precision and F1 value by 3.66 and 1.42 respectively compared to the baseline.
关键词
金融实体 /
情感极性 /
图卷积网络 /
交互信息表示
{{custom_keyword}} /
Key words
financial entities /
sentiment polarity /
convolutional network /
joint acquirement
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 刘宇瀚,刘常健,徐睿峰,等. 结合字形特征与迭代学习的金融领域命名实体识别[J].中文信息学报, 2020, 34(11): 74-83.
[2] 祝清麟,梁斌,徐睿峰,等. 结合金融领域情感词典和注意力机制的细粒度情感分析[J]. 中文信息学报, 2022,36(8):109-117.
[3] 任鹏飞,李旸,王素格, 等. 基于交互注意力的双图卷积网络的金融实体情感极性识别方法[J]. 中文信息学报,2023,37(12):129-137.
[4] WANG F, LAN M, WANG W. Towards a one-stop solution to both aspect extraction and sentiment analysis tasks with neural multi-task learning[C]//Proceedings of the International Joint Conference on Neural Networks, 2018: 1-8.
[5] LI X, BING L, LI P, et al. A unified model for opinion target extraction and target sentiment prediction[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, 2019: 6714-6721.
[6] YAN H, DAI J, JI T, et al. A unified generative framework for aspect-based sentiment analysis[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, 2021:2416-2429.
[7] ZHANG W, DENG Y, LI X, et al. Aspect-based sentiment analysis in question answering forums[C]//Proceedings of Conference on Empirical Methods in Natural Language Processing, 2021: 4582-4591.
[8] LUO H, LI T, LIU B, et al. DOER: Dual cross-shared RNN for aspect term polarity co-extraction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019:591-601.
[9] HE R, LEE W S, NG H T, et al. An interactive multi-task learning network for end-to-end aspect-based sentiment analysis[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019:504-515.
[10] CHEN Z, QIAN T. Relation-aware collaborative learning for unified aspect-based sentiment analysis[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020:3685-3694.
[11] LIANG Y, MENG F, ZHANG J, et al. An iterative multi-knowledge transfer network for aspect-based sentiment analysis[C]//Proceedings of Conference on Empirical Methods in Natural Language Processing, 2021: 1768-1780.
[12] WAN H, YANG Y, DU J, et al. Target-aspect-sentiment joint detection for aspect-based sentiment analysis[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence, 2020: 9122-9129.
[13] HU M, PENG Y, HUANG Z, et al. Open-domain targeted sentiment analysis via span-based extraction and classification[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: 537-546.
[14] LUO H, JI L, LI T, et al. GRACE: Gradient harmonized and cascaded labeling for aspect-based sentiment analysis [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 54-64.
[15] CHEN H, ZHAI Z, FENG F X, et al. Enhanced multi-channel graph convolutional network for aspect sentiment triplet extraction[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022: 2974-2985.
[16] CAI H J, XIA R, YU J F. Aspect category-opinion-sentiment quadruple extraction with implicit aspects and opinions[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021:340-350.
[17] ZHENG Z, ZHOU Z L, WANG Y N. SSEGCN: Syntactic and semantic enhanced graph convolutional network for aspect-based sentiment analysis[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022: 4916-4925.
[18] GOU Z B, GUO Q Y, YANG Y J. MVP: Multi-view prompting improves aspect sentiment tuple prediction[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023: 4380-4397.
[19] LI B, LIU Y, WANG X. Gradient harmonized sin gle-stage detector [C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, 2019: 8577- 8584.
[20] LI X, BING L, ZHANG W, et al. Exploiting BERT for end-to-end aspect-based sentiment analysis[C]//Proceedings of the 5th Workshop on Noisy User-generated Text, 2019: 34-41.
[21] CUI Y, CHE W, LIU T, et al. Pre-training with whole word masking for Chinese BERT[J]. Institute of Electrical and Electronics Engineers/Association for Computing Machinery Transactions on Audio, Speech, and Language Processing, 2021: 3504- 3514.
[22] MRINI K, DERNONCOURT F, TRAN Q, et al. Rethinking self-attention: An interpretable self-attentive encoder-decoder parser[J]. arXiv preprint arXiv: 1911.03875v1, 2019.
[23] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017:6000-6010.
[24] LI S, ZHAO Z, HU R, et al. Analogical reasoning on Chinese morphological and semantic relations[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018:138-143.
[25] DU Z X, QIAN Y J, LIU X, et al. GLM: General language model pretraining with autoregressive blank infilling[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022: 320-335.
[26] MIYATO T, DAI A M, GOODFELLOE I. Adversarial training methods for semi-supervised text classification[C]//Proceedings of the 5th International Conference on Learning Representations, 2017.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(62106130,62376143,62076158,62072294);山西省基础研究计划项目(20210302124084);山西省高等学校科技创新项目(2021L284);山西省重点实验室开放课题基金(CICIP2023006)
{{custom_fund}}
PDF(1272 KB)
