Filters








1,204 Hits in 6.2 sec

Recurrent Neural Networks with Auxiliary Labels for Cross-Domain Opinion Target Extraction

Ying Ding, Jianfei Yu, Jing Jiang
2017 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this work, we use rule-based unsupervised methods to create auxiliary labels and use neural network models to learn a hidden representation that works well for different domains.  ...  Opinion target extraction is a fundamental task in opinion mining. In recent years, neural network based supervised learning methods have achieved competitive performance on this task.  ...  Recurrent Neural Networks for Opinion Target Extraction In this section, we describe how we use recurrent neural networks for opinion target extraction.  ... 
doi:10.1609/aaai.v31i1.11014 fatcat:x4ysalfo2fao3kn3wohemykpaq

Syntactically-Meaningful and Transferable Recursive Neural Networks for Aspect and Opinion Extraction

Wenya Wang, Sinno Jialin Pan
2019 Computational Linguistics  
In the end, we integrate the recursive neural network with a sequence labeling classifier on top that models contextual influence in the final predictions.  ...  Specifically, the auxiliary task builds structural correspondences across domains by predicting the dependency relation for each path of the dependency tree in the recursive neural network.  ...  relations. • Hier-Joint: A cross-domain recurrent neural network proposed by Ding, Yu, and Jiang (2017) for aspect terms extraction across domains.  ... 
doi:10.1162/coli_a_00362 fatcat:topw3vnee5ao7aevhc6sd7axdq

Recursive Neural Structural Correspondence Network for Cross-domain Aspect and Opinion Co-Extraction

Wenya Wang, Sinno Jialin Pan
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Fine-grained opinion analysis aims to extract aspect and opinion terms from each sentence for opinion summarization. Supervised learning methods have proven to be effective for this task.  ...  However, in many domains, the lack of labeled data hinders the learning of a precise extraction model.  ...  A framework for learning predictive structures from multiple tasks and unlabeled data. JMLR 6:1817-1853. John Blitzer, Mark Dredze, and Fernando Pereira. 2007.  ... 
doi:10.18653/v1/p18-1202 dblp:conf/acl/PanW18 fatcat:oitt2xf2tjfg7py44zd7ehqzlu

Transferable Interactive Memory Network for Domain Adaptation in Fine-Grained Opinion Extraction

Wenya Wang, Sinno Jialin Pan
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
The source space and the target space are aligned through these domaininvariant interactions by incorporating an auxiliary task and domain adversarial networks.  ...  In fine-grained opinion mining, aspect and opinion terms extraction has become a fundamental task that provides key information for user-generated texts.  ...  Ding, Yu, and Jiang (2017) proposed to use auxiliary tasks as a supervision that are integrated into a recurrent neural network to learn shared representations for words across domains.  ... 
doi:10.1609/aaai.v33i01.33017192 fatcat:six4ap235jgdxkfw4p4leb4sbe

MITRE at SemEval-2016 Task 6: Transfer Learning for Stance Detection

Guido Zarrella, Amy Marsh
2016 Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)  
We employed a recurrent neural network initialized with features learned via distant supervision on two large unlabeled datasets.  ...  These sentence vectors were then finetuned for stance detection on several hundred labeled examples.  ...  Figure 1 : 1 A recurrent neural network for stance detection. Figure 2 : 2 F1 scores for each topic and class on both cross-validation and test conditions.  ... 
doi:10.18653/v1/s16-1074 dblp:conf/semeval/ZarrellaM16 fatcat:7l4sm7r27nhq5juqibbafa3mju

MITRE at SemEval-2016 Task 6: Transfer Learning for Stance Detection [article]

Guido Zarrella, Amy Marsh
2016 arXiv   pre-print
We employed a recurrent neural network initialized with features learned via distant supervision on two large unlabeled datasets.  ...  These sentence vectors were then fine-tuned for stance detection on several hundred labeled examples.  ...  Figure 1 : 1 A recurrent neural network for stance detection. Figure 2 : 2 F1 scores for each topic and class on both cross-validation and test conditions.  ... 
arXiv:1606.03784v1 fatcat:vydyis6imbaitglhhsjc7w2wze

Transition-based Adversarial Network for Cross-lingual Aspect Extraction

Wenya Wang, Sinno Jialin Pan
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
To solve it, we develop a novel deep model to transfer knowledge from a source language with labeled training data to a target language without any annotations.  ...  In fine-grained opinion mining, the task of aspect extraction involves the identification of explicit product features in customer reviews.  ...  These supervised methods all treat the problem as a sequence labeling task that work on each token in a sentence. For cross-domain aspect extraction, Li et al.  ... 
doi:10.24963/ijcai.2018/622 dblp:conf/ijcai/WangP18 fatcat:36pkvmr625ehxo2brwjfgrjbqe

Multitask Learning for Aspect-Based Sentiment Classification

Chunhua Yao, Xinyu Song, Xuelei Zhang, Weicheng Zhao, Ao Feng, Sze-Teng Liong
2021 Scientific Programming  
Specifically, we use opinion term extraction due to its high correlation with the main task.  ...  Through a custom-designed Cross Interaction Unit (CIU), effective information of the opinion term extraction task is passed to the main task, with performance improvement in both directions.  ...  instance with gold opinion extract labels.  ... 
doi:10.1155/2021/2055555 fatcat:5o5g5urmqjbgjo66nc5n32izpq

Leveraging Auxiliary Tasks for Document-Level Cross-Domain Sentiment Classification

Jianfei Yu, Jing Jiang
2017 International Joint Conference on Natural Language Processing  
In this paper, we study domain adaptation with a state-of-the-art hierarchical neural network for document-level sentiment classification.  ...  We then propose two neural network architectures to respectively induce document embeddings and sentence embeddings that work well for different domains.  ...  Acknowledgments We would like to thank the anonymous reviewers for their constructive comments.  ... 
dblp:conf/ijcnlp/YuJ17 fatcat:ssh3paza7za4znvqr2no6mwiuq

Issue Framing in Online Discussion Fora [article]

Mareike Hartmann and Tallulah Jansen and Isabelle Augenstein and Anders Søgaard
2019 arXiv   pre-print
, assuming only unlabeled training data in the target domain.  ...  In online discussion fora, speakers often make arguments for or against something, say birth control, by highlighting certain aspects of the topic.  ...  Titan Xp GPU used for this research.  ... 
arXiv:1904.03969v2 fatcat:rhwsnvlp6fcm5gi7z3b6t367lq

Issue Framing in Online Discussion Fora

Mareike Hartmann, Tallulah Jansen, Isabelle Augenstein, Anders Søgaard
2019 Proceedings of the 2019 Conference of the North  
, assuming only unlabeled training data in the target domain.  ...  In online discussion fora, speakers often make arguments for or against something, say birth control, by highlighting certain aspects of the topic.  ...  Titan Xp GPU used for this research.  ... 
doi:10.18653/v1/n19-1142 dblp:conf/naacl/HartmannJAS19 fatcat:vvwhfzjqsngrlkpal6bk7fcgwi

Deep Learning for Sentiment Analysis : A Survey [article]

Lei Zhang, Shuai Wang, Bing Liu
2018 arXiv   pre-print
Along with the success of deep learning in many other application domains, deep learning is also popularly used in sentiment analysis in recent years.  ...  Ltd with a research gift.  ...  Li et al. 47 proposed an adversarial memory network for cross-domain sentiment classification in a transfer learning setting, where the data from the source and the target domain are modelled together  ... 
arXiv:1801.07883v2 fatcat:nplicfgaozb6fbfx4eyts4zt7e

Weakly-supervised Domain Adaption for Aspect Extraction via Multi-level Interaction Transfer [article]

Tao Liang, Wenya Wang, Fengmao Lv
2020 arXiv   pre-print
Comprehensive experiments demonstrate that our approach can fully utilize sentence-level aspect category labels to improve cross-domain aspect extraction with a large performance gain.  ...  Fine-grained aspect extraction is an essential sub-task in aspect based opinion analysis. It aims to identify the aspect terms (a.k.a. opinion targets) of a product or service in each sentence.  ...  with Auxiliary Labels from [16] .  ... 
arXiv:2006.09235v1 fatcat:t6diemitzfe2fneaq5lmixbci4

Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning

Zheng Li, Xin Li, Ying Wei, Lidong Bing, Yu Zhang, Qiang Yang
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem.  ...  Dual adversarial neural transfer for low-resource named entity recognition. In ACL, pages 3461-3471.  ...  to common opinion words and syntactic relations. • Hier-Joint (Ding et al., 2017) : A recurrent neural network (RNN) with manually designed rule-based auxiliary tasks based on common syntactic relations  ... 
doi:10.18653/v1/d19-1466 dblp:conf/emnlp/LiLWBZY19 fatcat:i2g3iouz3nc5zgzrvoa2k6yb5y

Enhancing Aspect-based Sentiment Classification with Auxiliary Sentence and Domain Knowledge

Jindian Su, Shanshan Yu, Da Luo
2020 IEEE Access  
After that, XLNetCN also employs a capsule network with the dynamic routing algorithm to extract the local and spatial hierarchical relations of the text sequence, and yield its local feature representations  ...  Existing feature-based neural approaches for aspect-based sentiment analysis (ABSA) try to improve their performance with pre-trained word embeddings and by modeling the relations between the text sequence  ...  A multiple-attention based model that non-linearly combines the results of multiple attentions with a recurrent neural network, which provides a tailor-made memory for different opinion targets of a sentence  ... 
doi:10.1109/access.2020.2997675 fatcat:igsh3o2fijdtrgb23njzmldrhm
« Previous Showing results 1 — 15 out of 1,204 results