Filters








37,895 Hits in 4.7 sec

Correlation-Guided Representation for Multi-Label Text Classification

Qian-Wen Zhang, Ximing Zhang, Zhao Yan, Ruifang Liu, Yunbo Cao, Min-Ling Zhang
2021 Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence   unpublished
Multi-label text classification is an essential task in natural language processing.  ...  In this paper, we view the task as a correlation-guided text representation problem: an attention-based two-step framework is proposed to integrate text information and label semantics by jointly learning  ...  We propose an effective and novel method, called CORE, which exploits COrrelation-guided REpresentation for multi-label text classification.  ... 
doi:10.24963/ijcai.2021/463 fatcat:mlsyqh7nfvf7ni3cmg4tvskiky

Tailor Versatile Multi-modal Learning for Multi-label Emotion Recognition [article]

Yi Zhang, Mingyuan Chen, Jundong Shen, Chongjun Wang
2022 arXiv   pre-print
In this paper, we propose versaTile multi-modAl learning for multI-labeL emOtion Recognition (TAILOR), aiming to refine multi-modal representations and enhance discriminative capacity of each label.  ...  Multi-modal Multi-label Emotion Recognition (MMER) aims to identify various human emotions from heterogeneous visual, audio and text modalities.  ...  Correlation-Guided Representation for Chen, G. 2020a. Collaboration Based Multi-Label Propaga- Multi-Label Text Classification. In IJCAI, 3363–3369. tion for Fraud Detection.  ... 
arXiv:2201.05834v1 fatcat:ua2xxwh7ezcuvd2o2sbexymbmi

Tailor Versatile Multi-Modal Learning for Multi-Label Emotion Recognition

Yi Zhang, Mingyuan Chen, Jundong Shen, Chongjun Wang
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we propose versaTile multi-modAl learning for multI-labeL emOtion Recognition (TAILOR), aiming to refine multi-modal representations and enhance discriminative capacity of each label.  ...  Multi-modal Multi-label Emotion Recognition (MMER) aims to identify various human emotions from heterogeneous visual, audio and text modalities.  ...  Each pair of modalities interacts and correlates valuable information step by step. Label-Guided Decoder Label correlations plays an important role in effective multi-label classification.  ... 
doi:10.1609/aaai.v36i8.20895 fatcat:owtqgkwyu5f5pkzupe4uufw57m

Dual Adversarial Graph Neural Networks for Multi-label Cross-modal Retrieval

Shengsheng Qian, Dizhan Xue, Huaiwen Zhang, Quan Fang, Changsheng Xu
2021 AAAI Conference on Artificial Intelligence  
Secondly, we leverage the multi-hop graph neural networks, in which a layer aggregation mechanism is proposed to exploit multi-hop propagation information, to capture the label correlation dependency and  ...  and discriminative common representations for cross-modal retrieval.  ...  GNN to hierarchically explore and capture the label correlation dependency, which can learn modality-invariant and discriminative representation for multi-label cross-modal retrieval. • We propose a novel  ... 
dblp:conf/aaai/QianXZFX21 fatcat:7obepxisurfidp77apk45begoe

Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning [article]

Ximing Zhang, Qian-Wen Zhang, Zhao Yan, Ruifang Liu, Yunbo Cao
2021 arXiv   pre-print
In multi-label text classification (MLTC), each given document is associated with a set of correlated labels.  ...  We first utilize a joint embedding (JE) mechanism to obtain the text and label representation simultaneously.  ...  Acknowledgements We would like to thank the ACL reviewers for their valuable comments and Keqing He, Haoyan Liu, Zizhen Wang, Chenyang Liao and Rui Pan for their generous help and discussion.  ... 
arXiv:2106.03103v1 fatcat:ivu3g432lnbqto2vmkmhubj2we

Label-Specific Document Representation for Multi-Label Text Classification

Lin Xiao, Xin Huang, Boli Chen, Liping Jing
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)  
Multi-label text classification (MLTC) aims to tag most relevant labels for the given document.  ...  LSAN takes advantage of label semantic information to determine the semantic connection between labels and document for constructing labelspecific document representation.  ...  Acknowledgments We would like to thank the outstanding anonymous reviewers for their helpful comments to improve our manuscript. This work was supported in part by the National Natural Science  ... 
doi:10.18653/v1/d19-1044 dblp:conf/emnlp/XiaoHCJ19 fatcat:ckjkzcwj5rgtdmdcdjh5xyf5ne

Multi-level Deep Correlative Networks for Multi-modal Sentiment Analysis

Guoyong Cai, Guangrui Lyu, Yuming Lin, Yimin Wen
2020 Chinese journal of electronics  
First, the most relevant cross-modal feature representation is generated with Multi-modal Deep and discriminative correlation analysis (Multi-DDCA) while keeping those respective modal feature representations  ...  Second, the high-level semantic outputs from multi-modal deep and discriminative correlation analysis are encoded into attention-correlation cross-modal feature representation through a co-attention-based  ...  based feature representations to perform again the textual-guided visual attention and visual-guided textual attention. 2) Results and analysis It indicates that use deep multi-discriminant correlation  ... 
doi:10.1049/cje.2020.09.003 fatcat:rru2dat5prgixpq4ni6doqbpfa

Beyond Statistical Relations: Integrating Knowledge Relations into Style Correlations for Multi-Label Music Style Classification [article]

Qianwen Ma, Chunyuan Yuan, Wei Zhou, Jizhong Han, Songlin Hu
2021 arXiv   pre-print
Recently, some researches explore review-driven multi-label music style classification and exploit style correlations for this task.  ...  Automatically labeling multiple styles for every song is a comprehensive application in all kinds of music websites.  ...  ACKNOWLEDGEMENT We gratefully thank the anonymous reviewers for their insightful comments.  ... 
arXiv:1911.03626v2 fatcat:36dvbnd47zb6vfp72buvanv7ui

Modeling Label Semantics for Predicting Emotional Reactions [article]

Radhika Gaonkar, Heeyoung Kwon, Mohaddeseh Bastan, Niranjan Balasubramanian, Nathanael Chambers
2020 arXiv   pre-print
Predicting how events induce emotions in the characters of a story is typically seen as a standard multi-label classification task, which usually treats labels as anonymous classes to predict.  ...  We also introduce a new semi-supervision strategy that regularizes for the correlations on unlabeled data.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.  ... 
arXiv:2006.05489v2 fatcat:fwfwp7uk65b3ffasbwwt32px24

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion [article]

Yang Wang
2020 arXiv   pre-print
With the development of web technology, multi-modal or multi-view data has surged as a major stream for big data, where each modal/view encodes individual property of data objects.  ...  Throughout this survey, we further indicate that the critical components for this field go to collaboration, adversarial competition and fusion over multi-modal spaces.  ...  Multi-Modal CNN for Multi-Instance Multi-Label (MMCNN-MIML) [106] first generated multimodal instances from the image and text description.  ... 
arXiv:2006.08159v1 fatcat:g4467zmutndglmy35n3eyfwxku

Academic Resource Text Level Multi-label Classification based on Attention [article]

Yue Wang, Yawen Li, Ang Li
2022 arXiv   pre-print
Hierarchical multi-label academic text classification (HMTC) is to assign academic texts into a hierarchically structured labeling system.  ...  We propose an attention-based hierarchical multi-label classification algorithm of academic texts (AHMCA) by integrating features such as text, keywords, and hierarchical structure, the academic documents  ...  resources texts is suitable for the use of hierarchical multi-label classification.  ... 
arXiv:2203.10743v1 fatcat:badnoix3jveqhn7xc4vqurt5tq

Latent Emotion Memory for Multi-Label Emotion Classification

Hao Fei, Yue Zhang, Yafeng Ren, Donghong Ji
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we propose a Latent Emotion Memory network (LEM) for multi-label emotion classification.  ...  Existing methods usually model the problem as multi-label classification task. However, previous methods have two issues, limiting the performance of the task.  ...  To address these issues, we propose a Latent Emotion Memory network (LEM) for multi-label emotion classification.  ... 
doi:10.1609/aaai.v34i05.6271 fatcat:rdm66lb47bcunjzxldxl2pt5p4

Sound-Guided Semantic Image Manipulation [article]

Seung Hyun Lee, Wonseok Roh, Wonmin Byeon, Sang Ho Yoon, Chan Young Kim, Jinkyu Kim, Sangpil Kim
2021 arXiv   pre-print
Our audio encoder is trained to produce a latent representation from an audio input, which is forced to be aligned with image and text representations in the multi-modal embedding space.  ...  The experiments on zero-shot audio classification and semantic-level image classification show that our proposed model outperforms other text and sound-guided state-of-the-art methods.  ...  We use various text synonyms for a fair comparison, but text-guided latent code seems less effective with changes. Multi-modal Image Manipulation.  ... 
arXiv:2112.00007v1 fatcat:rcv7bt5ppvfihc57kqfa4d2pau

Multilingual Text Classification for Dravidian Languages [article]

Xiaotian Lin, Nankai Lin, Kanoksak Wattanachote, Shengyi Jiang, Lianxi Wang
2021 arXiv   pre-print
Hence, to address these problems, we proposed a multilingual text classification framework for the Dravidian languages.  ...  On the other hand, in view of the problem that the model cannot well recognize and utilize the correlation among languages, we further proposed a language-specific representation module to enrich semantic  ...  They also proposed joint label classification and multi-language joint training methods to improve classification performance for label marginalization problems.  ... 
arXiv:2112.01705v1 fatcat:sgmmquswcnh2jo3geerqarjv3u

Deep Correlated Predictive Subspace Learning for Incomplete Multi-View Semi-Supervised Classification

Zhe Xue, Junping Du, Dawei Du, Wenqi Ren, Siwei Lyu
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
DCPSL is able to learn proper subspace representation that is suitable for class label prediction, which can further improve the performance of classification.  ...  To address this problem, we propose a Deep Correlated Predictive Subspace Learning (DCPSL) method for incomplete multi-view semi-supervised classification.  ...  Deep Correlated Subspace Learning To learn the proper multi-view representation for semisupervised classification, three factors should be considered.  ... 
doi:10.24963/ijcai.2019/559 dblp:conf/ijcai/XueDDRL19 fatcat:jzqvhry3rvahngqygepjjmkd4i
« Previous Showing results 1 — 15 out of 37,895 results