当前位置: X-MOL 学术Cognit. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Sentic Computing for Aspect-Based Opinion Summarization Using Multi-Head Attention with Feature Pooled Pointer Generator Network
Cognitive Computation ( IF 4.3 ) Pub Date : 2021-02-04 , DOI: 10.1007/s12559-021-09835-8
Akshi Kumar , Simran Seth , Shivam Gupta , Shivam Maini

Neural sequence to sequence models have achieved superlative performance in summarizing text. But they tend to generate generic summaries that under-represent the opinion-sensitive aspects of the document. Additionally, the sequence to sequence models are prone to test-train discrepancy (exposure-bias) arising from the differential summary decoding processes in the training and testing phases. The models use ground truth summary words in the decoder training phase and predicted outputs in the testing phase. This inconsistency leads to error accumulation and substandard performance. To address these gaps, a cognitive aspect-based opinion summarizer, Feature Pooled Pointer Generator Network (FP2GN), is proposed which selectively attends to thematic and contextual cues to generate sentiment-aware review summaries. This study augments the pointer generator framework with opinion feature extraction, feature pooling, and mutual attention mechanism for opinion summarization. The proposed model FP2GN identifies the aspect terms in review text using sentic computing (SenticNet 5 and concept frequency-inverse opinion frequency) and statistical feature engineering. These aspect terms are encoded into context embeddings using weighted average feature pooling, which is processed in a pointer-generator framework inspired stacked Bi-LSTM encoder–decoder model with multi-head self-attention. The decoder system uses temporal and mutual attention mechanisms to ensure the appropriate representation of input-sequence. The study also proffers the use of teacher forcing ratio to curtail the exposure-bias-related error-accumulation. The model achieves ROUGE-1 score of 86.04% and ROUGE-L score of 88.51% on the Amazon Fine Foods dataset. An average gain of 2% over other methods is observed. The proposed model reinforces pointer generator network architecture with opinion feature extraction, feature pooling, and mutual attention mechanism to generate human-readable opinion summaries. Empirical analysis substantiates that the proposed model is better than the baseline opinion summarizers.



中文翻译:

基于特征集合指针生成器网络的多头注意力基于方面的观点汇总的Sentic计算

神经序列到序列模型在总结文本方面达到了最高的性能。但是,它们往往会生成通用摘要,这些摘要对文档中意见敏感方面的表示不足。另外,序列到序列模型易于在训练和测试阶段由差分摘要解码过程引起的测试-训练差异(曝光偏差)。这些模型在解码器训练阶段使用地面真相摘要字,在测试阶段使用预测的输出。这种不一致导致错误累积和性能不合格。为了解决这些差距,提出了一种基于认知方面的观点汇总器,特征池指针生成器网络(FP2GN),该网络有选择地关注主题和上下文提示,以生成可感知情绪的评论摘要。这项研究通过观点特征提取,特征池和相互关注机制进行观点总结来增强指针生成器框架。所提出的模型FP2GN使用sendic计算(SenticNet 5和概念频率-反意见频率)和统计特征工程来识别评论文本中的方面术语。这些方面术语使用加权平均特征池编码到上下文嵌入中,并在指针生成器框架启发下以具有多头自注意力的堆叠式Bi-LSTM编码器-解码器模型进行处理。解码器系统使用时间和相互注意机制来确保输入序列的适当表示。该研究还提供了使用 所提出的模型FP2GN使用sendic计算(SenticNet 5和概念频率-反意见频率)和统计特征工程来识别评论文本中的方面术语。这些方面术语使用加权平均特征池编码到上下文嵌入中,并在指针生成器框架启发下以具有多头自注意力的堆叠式Bi-LSTM编码器-解码器模型进行处理。解码器系统使用时间和相互注意机制来确保输入序列的适当表示。该研究还提供了使用 所提出的模型FP2GN使用sendic计算(SenticNet 5和概念频率-反意见频率)和统计特征工程来识别评论文本中的方面术语。这些方面术语使用加权平均特征池编码到上下文嵌入中,并在指针生成器框架启发下以具有多头自注意力的堆叠式Bi-LSTM编码器-解码器模型进行处理。解码器系统使用时间和相互注意机制来确保输入序列的适当表示。该研究还提供了使用 这些方面术语使用加权平均特征池编码到上下文嵌入中,并在指针生成器框架启发下以具有多头自注意的堆叠式Bi-LSTM编码器-解码器模型进行处理。解码器系统使用时间和相互注意机制来确保输入序列的适当表示。该研究还提供了使用 这些方面术语使用加权平均特征池编码到上下文嵌入中,并在指针生成器框架启发下以具有多头自注意力的堆叠式Bi-LSTM编码器-解码器模型进行处理。解码器系统使用时间和相互注意机制来确保输入序列的适当表示。该研究还提供了使用教师强迫比率以减少与曝光偏差相关的错误累积。该模型在Amazon Fine Foods数据集上的ROUGE-1得分为86.04%,ROUGE-L得分为88.51%。与其他方法相比,平均增益为2%。所提出的模型通过观点特征提取,特征池和相互关注机制来增强指针生成器网络体系结构,以生成易于理解的观点摘要。实证分析证实了所提出的模型比基线意见总结者更好。

更新日期:2021-02-04
down
wechat
bug