基于课程学习的跨度级方面情感三元组提取

doi:10.3785/j.issn.1008-973X.2025.01.008

浙江大学学报(工学版)

2025, Vol. 59

Issue (1): 79-88 DOI: 10.3785/j.issn.1008-973X.2025.01.008

计算机与控制工程

基于课程学习的跨度级方面情感三元组提取

侯明泽(

),饶蕾*(

),范光宇,陈年生,程松林

上海电机学院电子信息学院，上海 201306

Span-level aspect sentiment triplet extraction based on curriculum learning

Mingze HOU(

),Lei RAO*(

),Guangyu FAN,Niansheng CHEN,Songlin CHENG

School of Electronic Information Engineering Shanghai Dianji University, Shanghai 201306, China

全文: PDF(875 KB) HTML

摘要：

现有方面情感三元组提取方法存在无法充分利用预训练模型知识，容易出现过拟合或欠拟合，识别语句细粒度方面词和情感极性的能力不足等问题，为此提出基于课程学习框架的跨度级方面情感三元组提取方法. 该方法基于课程学习框架进行数据预处理，使用预训练模型学习句子的上下文表示，搭建跨度模型提取句子中所有可能的跨度，基于双通道提取方面词和意见词，筛出正确的方面词和意见词组合进行情感分类. 在ASTE-Data-V2数据集上的实验结果表明，所提方法的F1值比SPAN-ASTE的F1值提升了2个百分点，所提方法的实验结果优于GTS、B-MRC、JET等其他方面情感三元组提取方法.

关键词： 课程学习; 跨度模型; 方面情感三元组提取; 双通道; 情感分类

Abstract:

Exiting methods of aspect sentiment triplet extraction suffer from the problems of not being able to fully utilize the knowledge of the pre-trained model, being prone to overfitting or underfitting, and having insufficient ability to recognize the fine-grained aspects and sentiments of an utterance. A method for extracting span-level aspect sentiment triples based on a curriculum learning framework was proposed. Data preprocessing was performed based on the curriculum learning framework, and the contextual representation of a sentence was learned using a pre-trained model. By building a span model, all possible spans were extracted in a sentence. Aspect and opinion terms were extracted based on the dual channel, and the correct combinations of aspect-opinion were filtered out for sentiment categorization. Experimental results on the ASTE-Data-V2 dataset show that the F1 value of the proposed method is improved by 2 percentage points over that of SPAN-ASTE. The experimental results of the proposed method outperform the other aspect sentiment triplet extraction methods such as GTS, B-MRC, and JET.

Key words: curriculum learning span model aspect sentiment triplet extraction dual-channel sentiment categorization

收稿日期: 2023-11-19 出版日期: 2025-01-18

CLC:

TP 391.1

基金资助: 国家自然科学基金资助项目（61702320）.

通讯作者: 饶蕾 E-mail: 226003010119@st.sdju.edu.cn;raol@sdju.edu.cn

作者简介: 侯明泽（1999—），男，硕士生，从事自然语言处理研究. orcid.org/0009-0005-7768-7159. E-mail：226003010119@st.sdju.edu.cn

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	作者相关文章
	侯明泽
	饶蕾
	范光宇
	陈年生
	程松林

引用本文:

侯明泽,饶蕾,范光宇,陈年生,程松林. 基于课程学习的跨度级方面情感三元组提取[J]. 浙江大学学报(工学版), 2025, 59(1): 79-88.

Mingze HOU,Lei RAO,Guangyu FAN,Niansheng CHEN,Songlin CHENG. Span-level aspect sentiment triplet extraction based on curriculum learning. Journal of ZheJiang University (Engineering Science), 2025, 59(1): 79-88.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2025.01.008 或 https://www.zjujournals.com/eng/CN/Y2025/V59/I1/79

图 1 课程学习框架

图 2 基于课程学习框架的跨度级方面情感三元组提取方法的网络架构

图 3 课程学习在方面情感三元组提取任务中的训练过程

表 1 方面情感三元组提取数据集

图 4 ASTE-Data-V2不同子数据集中的句子长度统计图

表 2 GAS引入课程学习框架前后的方面情感三元组提取结果

表 3 Span-ASTE引入课程学习框架前后的方面情感三元组提取结果

表 4 BARTABSA引入课程学习框架前后的方面情感三元组提取结果

表 5 SBN引入课程学习框架前后的方面情感三元组提取结果

表 6 不同模型的方面情感三元组提取任务结果对比

图 5 预训练模型的差异分析

图 6 RoBERTa模型的训练损失函数曲线对比图

1	PENG H, XU L, BING L, et al. Knowing what, how and why: a near complete solution for aspect-based sentiment analysis [C]// Proceedings of the AAAI Conference on Artificial Intelligence . Palo Alto: AAAI, 2020, 34(5): 8600–8607.
2	XU L, LI H, LU W, et al. Position-aware tagging for aspect sentiment triplet extraction [EB/OL]. (2021–03–09) [2024–01–29]. https://arxiv.org/abs/2010.02609.
3	YAN H, DAI J, QIU X, et al. A unified generative framework for aspect-based sentiment analysis [EB/OL]. (2021–06–08) [2024–01–29]. https://arxiv.org/abs/2106.04300.
4	ZHANG W, LI X, DENG Y, et al. Towards generative 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) . [S.l.]: Association for Computational Linguistics, 2021: 504–510.
5	CHEN S, WANG Y, LIU J, et al. Bidirectional machine reading comprehension for aspect sentiment triplet extraction [C]// Proceedings of the AAAI Conference on Artificial Intelligence . Palo Alto: AAAI, 2021, 35(14): 12666–12674.
6	MAO Y, SHEN Y, YU C, et al. A joint training dual-MRC framework for aspect based sentiment analysis [C]// Proceedings of the AAAI Conference on Artificial Intelligence . Palo Alto: AAAI, 2021, 35(15): 13543–13551.
7	XU L, CHIA Y K, BING L. Learning span-level interactions for aspect sentiment triplet extraction [EB/OL]. (2021–07–26) [2024–01–29]. https://arxiv.org/abs/2107.12214.
8	CHEN Z, QIAN T. Bridge-based active domain adaptation for aspect term extraction [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) . [S.l.]: Association for Computational Linguistics, 2021: 317–327.
9	SUN K, ZHANG R, MENSAH S, et al. Aspect-level sentiment analysis via convolution over dependency tree [C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing . Hong Kong: Association for Computational Linguistics, 2019: 5679–5688.
10	ZHANG C, LI Q, SONG D. Aspect-based sentiment classification with aspect-specific graph convolutional networks [EB/OL]. (2019–10–13) [2024–01–29]. https://arxiv.org/abs/1909.03477.
11	PONTIKI M, GALANIS D, PAVLOPOULOS J, et al. SemEval-2014 task 4: aspect based sentiment analysis [C]// Proceeding of the 8th International Workshop on Semantic Evaluation . Dublin: Association for Computational Linguistics, 2014: 27–35.
12	PONTIKI M, GALANIS D, PAPAGEORGIOU H, et al. SemEval-2015 task 12: aspect based sentiment analysis [C]// Proceedings of the 9th International Workshop on Semantic Evaluation . Denver: Association for Computational Linguistics, 2015: 486–495.
13	PONTIKI M, GALANIS D, PAPAGEORGIOU H, et al. SemEval-2016 task 5: aspect based sentiment analysis [C]// Proceedings of the 10th International workshop on Semantic Evaluation . San Diego: Association for Computational Linguistics, 2016: 19–30.
14	BENGIO Y, LOURADOUR J, COLLOBERT R, et al. Curriculum learning [C]// Proceedings of the 26th Annual International Conference on Machine Learning . [S.l.]: Association for Computing Machinery, 2009: 41–48.
15	WANG X, CHEN Y, ZHU W A survey on curriculum learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44 (9): 4555- 4576
16	PLATANIOS E A, STRETCU O, NEUBIG G, et al. Competence-based curriculum learning for neural machine translation [EB/OL]. (2019–03–06) [2024–01–29]. https://arxiv.org/abs/1903.09848.
17	TAY Y, WANG S, TUAN L A, et al. Simple and effective curriculum pointer-generator networks for reading comprehension over long narratives [EB/OL]. (2019–05–26) [2024–01–29]. https://arxiv.org/abs/1905.10847.
18	LIU Y, OTT M, GOYAL N, et al. RoBERTa: a robustly optimized BERT pretraining approach [EB/OL]. (2019–07–26) [2024–01–29]. https://arxiv.org/abs/1907.11692.
19	KOCMI T, BOJAR O. Curriculum learning and minibatch bucketing in neural machine translation [EB/OL]. (2017–07–29) [2024–01–29]. https://arxiv.org/abs/1707.09533.
20	DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding [EB/OL]. (2019–05–24) [2024–01–29]. https://arxiv.org/abs/1810.04805.
21	WU Z, YING C, ZHAO F, et al. Grid tagging scheme for aspect-oriented fine-grained opinion extraction [EB/OL]. (2020–11–03) [2024–01–29]. http://arxiv.org/abs/2010.04640.
22	RAFFEL C, SHAZEER N, ROBERTS A, et al. Exploring the limits of transfer learning with a unified text-to-text transformer [J]. The Journal of Machine Learning Research , 2020, 21: 1–67.
23	LEWIS M,LIU Y,GOYAL N,et al. BART: denoising swquence-to-sequence pre-training for natural language generation, translation, and comprehension [EB/OL]. (2019–10–29)[2024–01–29]. https://arxiv.org/abs/1910.13461.
24	CHEN Y, KEMING C, SUN X, et al. A span-level bidirectional network for aspect sentiment triplet extraction [C]// Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing . Abu Dhabi: Association for Computational Linguistics, 2022: 4300–4309.
25	JANOCHA K, CZARNECKI W M. On loss functions for deep neural networks in classification [EB/OL]. (2017–02–18) [2024–01–29]. https://arxiv.org/abs/1702.05659.

[1]	周聪聪，涂春龙，高云，王飞翔，何成，龚红伟，连平, 叶学松. 腕戴式低功耗无线心率监测装置的研制[J]. 浙江大学学报(工学版), 2015, 49(4): 798-806.

Viewed

Full text

Abstract

Cited

Shared

Discussed