Aspect-based sentiment analysis (ABSA) aims to identify users’ opinions expressed about specific text aspects using elements such as aspect words, opinion words, and sentiment polarity. However, the existing research mainly focuses on individual tasks, which neglects feature interactions between different parts and causes error propagation issues. A sentiment triplet extraction method based on a multi-feature weighted graph convolutional network is proposed to jointly model multiple subtasks. Then, a double affine attention module is employed to capture the relational probability distribution among word pairs. Additionally, prior information such as text semantics, syntax, and location is encoded into multi-feature vectors. Finally, graph convolution operations are utilized for achieving multi-feature fusion and realizing the joint extraction of aspect term-opinion term-sentiment polarity. Through the estimation test based on 2 benchmark datasets, the experimental results reveal that the sentiment triplet extraction method based on a multi-feature weighted graph convolutional network can effectively alleviate the error propagation issues in pipeline methods. Moreover, feature interaction among each factor of the triplet set is proposed, and it is proved that the model in the current work performs much better than the previous benchmark model at triplet extraction.
此外,考虑到方面术语与上下文或意见术语之间存在特定的句法依赖关系, 这些语言知识可以为方面情感三元组抽取任务提供丰富的指示信息. 如图1所示,对于目标文本“The weather was gloomy, but the food was tasty.”,为了判断方面术语的情感极性,意见术语“gloomy”必须准确匹配单词“weather”,因而需要根据单词之间的句法依存关系来学习任务相关的特征表示. 通常评论文本中的方面术语是名词或名词短语, 意见术语是动词或形容词, “food”是“tasty”的名词主语, 两者间依赖类型为“nsubj”. 因此, 引入语法依赖不仅有助于提取方面术语和意见术语, 还利于两者之间的匹配.
本文提出了一种基于句法依赖和位置距离加权图卷积网络的ASTE模型(model based on syntactic dependence and positional distance weighted graph convolution network for ASTE, SPW-GCN).模型整体架构如图2所示,主要由编码层、加权图卷积层、约束推理层、解码预测层和输出层5部分组成.
PHANM H, OGUNBONAP O .Modelling context and syntactical features for aspect-based sentiment analysis[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Online.Stroudsburg,PA,USA:Association for Computational Linguistics,2020: 3211-3220.
[2]
PENGH Y, XUL, BINGL D,et al .Knowing what,how and why:a near complete solution for aspect-based sentiment analysis[J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(5):8600-8607.
[3]
MAOY, SHENY, YUC,et al .A joint training dual-MRC framework for aspect based sentiment analysis[J].Proceedings of the AAAI Conference on Artificial Intelligence,2021,35(15):13543-13551.
[4]
CHENS W, WANGY, LIUJ,et al .Bidirectional machine reading comprehension for aspect sentiment triplet extraction[J].Proceedings of the AAAI Conference on Artificial Intelligence,2021,35(14): 12666-12674.
[5]
ZHANGC, LIQ C, SONGD W,et al .A multi-task learning framework for opinion triplet extraction[C]//Findings of the Association for Computational Linguistics:EMNLP 2020.Online.Stroudsburg,PA,USA:Association for Computational Linguistics, 2020: 819-828.
[6]
XUL, LIH, LUW, et al. Position-aware tagging for aspect sentiment triplet extraction[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Online. Stroudsburg,PA,USA:Association for Computational Linguistics, 2020: 2339-2349.
[7]
WUZ, YINGC C, ZHAOF,et al .Grid tagging scheme for aspect-oriented fine-grained opinion extraction[C]//Findings of the Association for Computational Linguistics:EMNLP 2020.Online.Stroudsburg,PA,USA:Association for Computational Linguistics, 2020: 2576-2585.
[8]
CHENZ X, HUANGH, LIUB,et al .Semantic and syntactic enhanced aspect sentiment triplet extraction[J].ArXiv e-Prints,2021:arXiv:2106.03315.
[9]
BAI JIANS Y, NAYAKT, MAJUMDERN,et al .Aspect sentiment triplet extraction using reinforcement learning[J].ArXiv e-Prints,2021:arXiv:2108.06107.
[10]
YANH, DAIJ Q, JIT,et al .A unified generative framework for aspect-based sentiment analysis[C]//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). Online. Stroudsburg, PA,USA:Association for Computational Linguistics,2021:2416-2429.
[11]
ZHAOY C, MENGK, LIUG S, et al. A multi-task dual-tree network for aspect sentiment triplet extraction[C]// Proceedings of the 29th International Conference on Computational Linguistics. Gyeongju, Republic of Korea. New York, NY: Association for Computing Machinery, 2022: 7065-7074.
[12]
ZHANGY C, YANGY F, LIY H, et al. Boundary-driven table-filling for aspect sentiment triplet extraction[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Abu Dhabi,United Arab Emirates. Stroudsburg, PA,USA: Association for Computational Linguistics, 2022: 6485-6498.
[13]
ZHANGC, LIQ C, SONGD W. Aspect-based sentiment classification with aspect-specific graph convolutional networks[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).Hong Kong,China.Stroudsburg,PA,USA:Association for Computational Linguistics,2019: 4568-4578.
[14]
DEVLINJ, CHANGM W, LEEK, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Florence,Italy.Stroudsburg,PA,USA:Association for Computational Linguistics, 2019: 4171-4186.
[15]
DOZATT, MANNINGC. Deep biaffine attention for neural dependency parsing[J]. ArXiv e-Prints,2021:arXiv: 1611. 01734.
[16]
QIP, ZHANGY H, ZHANGY H,et al .Stanza:a python natural language processing toolkit for many human languages[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics:System Demonstrations.Online.Stroudsburg,PA,USA:Association for Computational Linguistics,2020:101-108.
[17]
OH S, LEED, WHANGT,et al. Deep context-and relation-aware learning for aspect-based sentiment analysis[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2:Short Papers). Online. Stroudsburg, PA,USA:Association for Computational Linguistics,2021: 495-503.
[18]
PONTIKIM, GALANISD, PAVLOPOULOSJ,et al. SemEval-2014 task 4:aspect based sentiment analysis[C]//Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014.Dublin,Ireland.Stroudsburg,PA,USA:Association for Computational Linguistics, 2014: 27-35.
[19]
PONTIKIM, GALANISD, PAPAGEORGIOUH, et al. SemEval-2015 task 12: aspect based sentiment analysis[C]//Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015. Denver, Colorado. Stroudsburg, PA, USA: Association for Computational Linguistics, 2015: 486-495.
[20]
PONTIKIM, GALANISD, PAPAGEORGIOUH,et al. SemEval-2016 task 5:aspect based sentiment analysis[C]//Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). San Diego, California. Stroudsburg, PA, USA:Association for Computational Linguistics, 2016: 19-30.
[21]
LIX, BINGL D, LIP J, et al. A unified model for opinion target extraction and target sentiment prediction[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 6714-6721.
[22]
FANZ F, WUZ, DAIX Y,et al .Target-oriented opinion words extraction with target-fused neural sequence labeling[C]//Proceedings of the 2019 Conference of the North. Minneapolis,Minnesota. Stroudsburg,PA,USA:Association for Computational Linguistics, 2019: 2509-2518.
[23]
HER D, LEEW S, NGH 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.Florence,Italy.Stroudsburg,PA,USA:Association for Computational Linguistics, 2019: 504-515.
[24]
WANGW Y, PANS J, DAHLMEIERD,et al .Coupled multi-layer attentions for co-extraction of aspect and opinion terms[J].Proceedings of the AAAI Conference on Artificial Intelligence,2017,31(1): 3316-3322.
[25]
DAIH L, SONGY Q .Neural aspect and opinion term extraction with mined rules as weak supervision[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.Florence,Italy.Stroudsburg,PA,USA:Association for Computational Linguistics,2019:5268-5277.