Aspect Based Sentiment Analysis基于方面的情感分析(Aspect Based Sentiment Analysis)是一种细粒度的情感分析任务,旨在识别一条句子中一个指定方面(Aspect)的情感极性。一个句子中可能含有多个不同的方面,每个方面的情感极性可能不同。基于方面的情感分析有很多实际应用价值,如针对商品评论的基于方面的情感分析可以提取用户对一个商品不同部分/方面的评价,为厂商进一步改进商品提供更细粒度的参考。
Pinlong Zhao, Linlin Hou,Ou Wu
Knowledge-Based Systems, (2020): 105443
Sentiment Dependencies with Graph Convolutional Networks first adopts bidirectional attention mechanism with position encoding to obtain aspect-specific representations, captures the sentiment dependencies via message passing between aspects
Cited by6BibtexViews175DOI
0
0
EMNLP 2020, pp.3594-3605, (2020)
Aspect-based sentiment analysis is an advanced sentiment analysis task that aims to classify the sentiment towards a specific aspect
Cited by2BibtexViews283DOI
0
0
ACL, pp.3667-3677, (2020)
We propose a novel Cooperative Graph Attention Networks approach to Aspect Sentiment Classification
Cited by1BibtexViews375
0
0
ACL, pp.3685-3694, (2020)
Experiments on three realworld datasets demonstrate that our Relation-Aware Collaborative Learning framework with its two implementations outperforms the state-of-the-art pipeline and unified baselines for the complete Aspect-based sentiment analysis task
Cited by0BibtexViews170
0
0
Minh Hieu Phan,Philip O. Ogunbona
ACL, pp.3211-3220, (2020)
We proposed an end-to-end Aspect-based sentiment analysis solution which pipelined an aspect extractor and an aspect sentiment classifier
Cited by0BibtexViews185
0
0
ACL, pp.6578-6588, (2020)
We propose a dependency graph enhanced dual-transformer network by jointly considering the flat representations learnt from Transformer and graphbased representations learnt from the corresponding dependency graph in an iterative interaction manner
Cited by0BibtexViews384
0
0
Li Kun, Chen Chengbo,Quan Xiaojun,Ling Qing, Song Yan
ACL, pp.7056-7066, (2020)
We have presented a conditional data augmentation approach for aspect term extraction
Cited by0BibtexViews136
0
0
Wang Kai, Shen Weizhou, Yang Yunyi,Quan Xiaojun, Wang Rui
ACL, pp.3229-3238, (2020)
Experimental results on three public datasets showed that the connections between aspects and opinion words can be better established with relational graph attention network, and the performance of graph attention network and BERT are significantly improved as a result
Cited by0BibtexViews169
0
0
Mi Zhang, Tieyun Qian
EMNLP 2020, pp.3540-3549, (2020)
We propose a novel framework BiGCN to leverage the graph based methods for aspect level sentiment classification tasks
Cited by0BibtexViews237DOI
0
0
Liang Yunlong, Meng Fandong, Zhang Jinchao,Xu Jinan, Chen Yufeng, Zhou Jie
We propose a dependency syntactic knowledge augmented interactive architecture with multi-task learning, which is able to fully exploit the syntactic knowledge and simultaneously model multiple related tasks
Cited by0BibtexViews136
0
0
Liang Yunlong, Meng Fandong, Zhang Jinchao,Xu Jinan, Chen Yufeng, Zhou Jie
We propose an iterative knowledge transfer network for the Aspect-based sentiment analysis task, which can fully exploit the inter-task correlations among the three aspect-level subtasks with the proposed routing algorithm
Cited by0BibtexViews103
0
0
Bai Xuefeng, Liu Pengbo, Zhang Yue
We investigated the use of typed dependency structures for targeted sentiment classification, by extending a graph attention network encoder with relation features
Cited by0BibtexViews96
0
0
Chi Sun, Luyao Huang,Xipeng Qiu
North American Chapter of the Association for Computational Linguistics, (2019): 380-385
The BERT-pair-natural language inference-B model achieves the best performance for aspect category detection
Cited by159BibtexViews130
0
0
arXiv: Computation and Language, (2019)
We proposed a new task called review reading comprehension and investigated the possibility of turning reviews as a valuable resource for answering user questions
Cited by148BibtexViews181
0
0
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF AR..., (2019): 4253-4260
We explore a motivated direction for aspectlevel sentiment classification named coarse-to-fine task transfer and build a large-scale YelpAspect dataset as highly beneficial source benchmarks
Cited by48BibtexViews288
0
0
Meeting of the Association for Computational Linguistics, (2019)
We propose an interactive multi-task learning network IMN for jointly learning aspect and opinion term co-extraction, and aspect-level sentiment classification
Cited by38BibtexViews127
0
0
national conference on artificial intelligence, (2019): 6714-6721
We investigate the complete task of Target-Based Sentiment Analysis, which is formulated as a sequence tagging problem with a unified tagging scheme in this paper
Cited by27BibtexViews145DOI
0
0
Youwei Song,Jiahai Wang, Tao Jiang, Zhiyue Liu, Yanghui Rao
arXiv: Computation and Language, (2019)
To deal with the label unreliability issue, we employ a label smoothing regularization to encourage the model to be less confident with fuzzy labels
Cited by26BibtexViews122
0
0
EMNLP, pp.1091-1096, (2019)
We introduce two novel neural units called parameterized filter and parameterized gate to incorporate aspect information into the convolutional neural network architecture
Cited by26BibtexViews138
0
0
EMNLP/IJCNLP (1), pp.4589-4599, (2019)
The proposed Selective Adversarial Learning method can be potentially extended to other domain adaptation methods and applied to more general sequence labeling tasks including named entity recognition, part-of-speech tagging, etc
Cited by24BibtexViews215DOI
0
0
小科