Attention Modeling for Targeted Sentiment

Liu, Jiangming; Zhang, Yue

doi:10.18653/v1/e17-2091

Cited by 207 publications

(93 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Text. The baselines (e.g., SVM [8], CNN [15], Transformer [36], and BiLSTM-Attention [18]) solely relied on textual information and didn't perform well. Correspondingly, most graphembedding approaches with different mechanisms can improve task performance.…”

Section: Experiments Results and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning

Jiang

Wang

Zhao

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Aspect category detection is an essential task for sentiment analysis and opinion mining. However, the cost of categorical data labeling, e.g., label the review aspect information for a large number of product domains, can be inevitable but unaffordable. In this study, we propose a novel problem, cross-domain aspect category transfer and detection, which faces three challenges: various feature spaces, different data distributions, and diverse output spaces. To address these problems, we propose an innovative solution, Traceable Heterogeneous Graph Representation Learning (THGRL). Unlike prior text-based aspect detection works, THGRL explores latent domain aspect category connections via massive user behavior information on a heterogeneous graph. Moreover, an innovative latent variable "Walker Tracer" is introduced to characterize the global semantic/aspect dependencies and capture the informative vertexes on the random walk paths. By using THGRL, we project different domains' feature spaces into a common one, while allowing data distributions and output spaces stay differently. Experiment results show that the proposed method outperforms a series of state-of-the-art baseline models.

show abstract

Section: Experiments Results and Analysismentioning

confidence: 99%

“…3. Bidirectional Recurrent Neural Network (BiLSTM) with Attention Mechanism [18]: We used a bidirectional LSTM to represent the word sequence in a review then calculated the weighted values over each word in reviews by an attention model. This baseline was denoted as BiLSTM-Attention.…”

Section: Experiments 41 Dataset and Experiments Settingmentioning

confidence: 99%

Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning

Jiang

Wang

Zhao

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

show abstract

“…Various neural models (Dong et al, 2014;Nguyen and Shirai, 2015;Vo and Zhang, 2015;Tang et al, 2016a,b;Wang et al, 2016;Liu and Zhang, 2017;Chen et al, 2017) have been proposed for aspect-level sentiment classification. The main idea behind these works is to develop neural architectures that are able to learn continuous features and capture the intricate relation between a target and context words.…”

Section: Related Workmentioning

confidence: 99%

Exploiting Document Knowledge for Aspect-level Sentiment Classification

Lee²,

Ng³

et al. 2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

242

210

View full text Add to dashboard Cite

Attention-based long short-term memory (LSTM) networks have proven to be useful in aspect-level sentiment classification. However, due to the difficulties in annotating aspect-level data, existing public datasets for this task are all relatively small, which largely limits the effectiveness of those neural models. In this paper, we explore two approaches that transfer knowledge from documentlevel data, which is much less expensive to obtain, to improve the performance of aspect-level sentiment classification. We demonstrate the effectiveness of our approaches on 4 public datasets from Se-mEval 2014, 2015, and 2016, and we show that attention-based LSTM benefits from document-level knowledge in multiple ways.

show abstract

“…We use the mean vector of a span hidden features as a target vector and apply dot-wise attention over the sentence hidden features. This kind of attention mechanism is widely used in targeted sentiment analysis [17,18].…”

Section: Sentence Featuresmentioning

confidence: 99%

Feature-Less End-to-End Nested Term Extraction

Gao

Yuan

2019

Natural Language Processing and Chinese Computing

View full text Add to dashboard Cite

In this paper, we proposed a deep learning-based end-toend method on domain specified automatic term extraction (ATE), it considers possible term spans within a fixed length in the sentence and predicts them whether they can be conceptual terms. In comparison with current ATE methods, the model supports nested term extraction and does not crucially need extra (extracted) features. Results show that it can achieve a high recall and a comparable precision on term extraction task with inputting segmented raw text.

show abstract

Attention Modeling for Targeted Sentiment

Cited by 207 publications

References 16 publications

Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning

Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning

Exploiting Document Knowledge for Aspect-level Sentiment Classification

Feature-Less End-to-End Nested Term Extraction

Contact Info

Product

Resources

About