Filters








604 Hits in 3.1 sec

Multinomial Adversarial Networks for Multi-Domain Text Classification [article]

Xilun Chen, Claire Cardie
2018 arXiv   pre-print
In this work, we propose a multinomial adversarial network (MAN) to tackle the text classification problem in this real-world multidomain setting (MDTC).  ...  Many text classification tasks are known to be highly domain-dependent. Unfortunately, the availability of training data can vary drastically across domains.  ...  In this paper, we thus propose Multinomial Adversarial Networks (henceforth, MANs) for the task of multi-domain text classification.  ... 
arXiv:1802.05694v1 fatcat:ipo3he2tnzdijifqmdggbptjtm

Multinomial Adversarial Networks for Multi-Domain Text Classification

Xilun Chen, Claire Cardie
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
In this work, we propose a multinomial adversarial network 1 (MAN) to tackle this real-world problem of multi-domain text classification (MDTC) in which labeled data may exist for multiple domains, but  ...  Many text classification tasks are known to be highly domain-dependent. Unfortunately, the availability of training data can vary drastically across domains.  ...  We also thank Yun Liu, Tianze Shi, Xun Huang, and the anonymous reviewers for their helpful feedback and/or discussions.  ... 
doi:10.18653/v1/n18-1111 dblp:conf/naacl/ChenC18 fatcat:f37v2nnebbdn3auia5s5y4hlly

Dual Adversarial Co-Learning for Multi-Domain Text Classification [article]

Yuan Wu, Yuhong Guo
2019 arXiv   pre-print
In this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC).  ...  The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneously  ...  ) (Liu, Qiu, and Huang 2016) , Multinomial Adversarial Networks for Multi-Domain Text Classification (MAN) (Chen and Cardie 2018) and Adversarial Multi-task Learning for Text Classification (ASP-MTL  ... 
arXiv:1909.08203v1 fatcat:rrnw2zpkqbeaxlatfhpvjerhg4

Dual Adversarial Co-Learning for Multi-Domain Text Classification

Yuan Wu, Yuhong Guo
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In order to address these issues, in this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC).  ...  The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneously  ...  RNN-MT) (Liu, Qiu, and Huang 2016) , Multinomial Adversarial Networks for Multi-Domain Text Classification (MAN) (Chen and Cardie 2018) and Adversarial Multi-task Learning for Text Classification (ASP-MTL  ... 
doi:10.1609/aaai.v34i04.6115 fatcat:jzetb7r4knb57mgn6xq33srfw4

Mixup Regularized Adversarial Networks for Multi-Domain Text Classification [article]

Yuan Wu, Diana Inkpen, Ahmed El-Roby
2021 arXiv   pre-print
Using the shared-private paradigm and adversarial training has significantly improved the performances of multi-domain text classification (MDTC) models.  ...  In this paper, we propose a mixup regularized adversarial network (MRAN) to address these two issues.  ...  CONCLUSION In this paper, we propose mixup regularized adversarial networks (MRANs) for multi-domain text classification.  ... 
arXiv:2102.00467v1 fatcat:jo5cbkcbpzgm5kk3reuepupdgm

Conditional Adversarial Networks for Multi-Domain Text Classification [article]

Yuan Wu, Diana Inkpen, Ahmed El-Roby
2021 arXiv   pre-print
shared features, for multi-domain text classification (MDTC).  ...  In this paper, we propose conditional adversarial networks (CANs), a framework that explores the relationship between the shared features and the label predictions to impose more discriminability to the  ...  Conclusion In this paper, we propose conditional adversarial networks (CANs) for multi-domain text classification.  ... 
arXiv:2102.10176v1 fatcat:cihqrvoicfhflkiu5rl6ezb7oe

TSAL: Two steps Adversarial learning based domain adaptation

Haidi Hasan Badr, Nayer Mahmoud Wanas, Magda Fayek
2021 Proceedings of the ... International Florida Artificial Intelligence Research Society Conference  
Adversarial learning is a strategy for learning domain-transferable features in robust deep networks. This paper introduces the TSAL paradigm, a two-step adversarial learning framework.  ...  It addresses the real-world problem of text classification, where source domain(s) has labeled data but target domain (s) has only unlabeled data.  ...  . • MAN (Chen and Cardie 2018) : it is a multinomial adversarial networks for multi-domain text classification. • DACL (Wu and Guo 2020) : dual adversarial co-learning approach for text classification  ... 
doi:10.32473/flairs.v34i1.128510 fatcat:6qpuq4tqlvhvbpfy3cai42rceu

A Robust Contrastive Alignment Method For Multi-Domain Text Classification [article]

Xuefeng Li, Hao Lei, Liwen Wang, Guanting Dong, Jinzheng Zhao, Jiachi Liu, Weiran Xu, Chunyun Zhang
2022 arXiv   pre-print
Multi-domain text classification can automatically classify texts in various scenarios.  ...  By this means, we only need two universal feature extractors to achieve multi-domain text classification.  ...  The adversarial multi-task learning for text classification (ASP-MTL) [5] .  ... 
arXiv:2204.12125v1 fatcat:qygov5vxsfeb5kwcu6t5oc5nha

Biomedical Relation Classification by single and multiple source domain adaptation

Sinchani Chakraborty, Sudeshna Sarkar, Pawan Goyal, Mahanandeeshwar Gattu
2019 Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)  
Relation classification is crucial for inferring semantic relatedness between entities in a piece of text. These systems can be trained given labelled data.  ...  Our experiments with the model have shown to improve state-of-the-art F1 score on 3 benchmark biomedical corpora for single domain and on 2 out of 3 for multi-domain scenarios.  ...  Besides, the authors would like to thank the anonymous reviewers for their valuable comments and feedback.  ... 
doi:10.18653/v1/d19-6210 dblp:conf/acl-louhi/ChakrabortySGG19 fatcat:77iupedcdjd4hl6rytmztpq5be

Investigating the Working of Text Classifiers [article]

Devendra Singh Sachan and Manzil Zaheer and Ruslan Salakhutdinov
2018 arXiv   pre-print
Text classification is one of the most widely studied tasks in natural language processing.  ...  Using various recent state-of-the-art approaches for text classification, we explore whether these models actually learn to compose the meaning of the sentences or still just focus on some keywords or  ...  We would also like to thank the anonymous reviewers for giving us their valuable feedback which helped to improve the paper.  ... 
arXiv:1801.06261v2 fatcat:d6i23rsofvclzkqd3owfh3y5ky

Comparative Study ofConvolutional Neural Network with Word Embedding Technique for Text Classification

Amol C. Adamuthe, Department of Information Technology, Rajarambapu Institute of Technology, Rajaramnagar, MS, India, Sneha Jagtap
2019 International Journal of Intelligent Systems and Applications  
This paper presents an investigation of the convolutional neural network (CNN) with Word2Vec word embedding technique for text classification.  ...  The paper presents convolutional neural network with word embedding technique for text classification. The main objective is divided into three sub-objectives,  ...  CNN has given better results for many problems from the medical domain [8] , social networks [6] , image classification and image analysis [7] .  ... 
doi:10.5815/ijisa.2019.08.06 fatcat:wv7i3y5shzdq7oafcsw3udlhnm

An Introduction to Robust Graph Convolutional Networks [article]

Mehrnaz Najafi, Philip S. Yu
2021 arXiv   pre-print
In this paper, we propose a novel Robust Graph Convolutional Neural Networks for possible erroneous single-view or multi-view data where data may come from multiple sources.  ...  Graph convolutional neural networks (GCNs) generalize tradition convolutional neural networks (CNNs) from low-dimensional regular graphs (e.g., image) to high dimensional irregular graphs (e.g., text documents  ...  Text documents on word embeddings, social networks or biological networks that can be represented as graphs lying on irregular Permission to make digital or hard copies of all or part of this work for  ... 
arXiv:2103.14807v1 fatcat:52zu625fdve4ln3oxwjxjxlea4

Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives [article]

Jing Han, Zixing Zhang, Nicholas Cummins, Björn Schuller
2018 arXiv   pre-print
Over the past few years, adversarial training has become an extremely active research topic and has been successfully applied to various Artificial Intelligence (AI) domains.  ...  We expect that this overview will help facilitate the development of adversarial training for affective computing and sentiment analysis in both the academic and industrial communities.  ...  In this regard, DANN variants have been proposed for multiple source domain adaptation [101] , multi-task learning [102] , and multinomial adversarial nets [103] .  ... 
arXiv:1809.08927v1 fatcat:m5mencegljgsphub3p62ltrhby

Deep visual unsupervised domain adaptation for classification tasks: a survey

Yeganeh Madadi, Vahid Seydi, Kamal Nasrollahi, Reshad Hosseini, Thomas B. Moeslund
2020 IET Image Processing  
This study surveys such domain adaptation methods that have been used for classification tasks in computer vision.  ...  Partial adversarial-based methods partial adversarial networks SAN [89], PADA [90], IWAN [91], ETN [92] Bold highlights three particular approaches.  ...  [165] proposed a multinomial adversarial network (MAN) to address the text recognition problem by using the adversarial approach.  ... 
doi:10.1049/iet-ipr.2020.0087 fatcat:x7v5et3r6nagpe2ivuu5nd4qku

Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives [Review Article]

Jing Han, Zixing Zhang, Bjorn Schuller
2019 IEEE Computational Intelligence Magazine  
o ver the past few years, adversarial training has become an extremely active research topic and has been successfully applied to various Artificial Intelligence (AI) domains.  ...  We expect that this overview will help facilitate the development of adversarial training for affective computing and sentiment analysis in both the academic and industrial communities.  ...  lIu eT Al. [102] 2018 DAT TexT ASpD FoR MulTI-TASK; SeMI-SupeRVISeD FRIeNDlY. CHeN & CARDIe [103] 2018 DAT TexT MulTINoMIAl ASpD MulTINoMIAl DISCRIMINAToR FoR MulTI-DoMAIN.  ... 
doi:10.1109/mci.2019.2901088 fatcat:edkvfgy3ofgufcytngf5mktpae
« Previous Showing results 1 — 15 out of 604 results