9 results on '"Huang, Heyan"'
Search Results
2. Leveraging Conceptualization for Short-Text Embedding.
- Author
-
Huang, Heyan, Wang, Yashen, Feng, Chong, Liu, Zhirun, and Zhou, Qiang
- Subjects
- *
SEMANTIC computing , *FINITE state machines , *MACHINE learning , *COMPUTER algorithms , *HUMAN-computer interaction , *AMBIENT intelligence - Abstract
Most short-text embedding models typically represent each short-text only using the literal meanings of the words, which makes these models indiscriminative for the ubiquitous polysemy. In order to enhance the semantic representation capability of the short-texts, we (i) propose a novel short-text conceptualization algorithm to assign the associated concepts for each short-text, and then (ii) introduce the conceptualization results into learning the conceptual short-text embeddings. Hence, this semantic representation is more expressive than some widely-used text representation models such as the latent topic model. Wherein, the short-text conceptualization algorithm used here is based on a novel co-ranking framework, enabling the signals (i.e., the words and the concepts) to fully interplay to derive the solid conceptualization for the short-texts. Afterwards, we further extend the conceptual short-text embedding models by utilizing an attention-based model that selects the relevant words within the context to make more efficient prediction. The experiments on the real-world datasets demonstrate that the proposed conceptual short-text embedding model and short-text conceptualization algorithm are more effective than the state-of-the-art methods. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
3. Labeled Phrase Latent Dirichlet Allocation and its online learning algorithm.
- Author
-
Tang, Yi-Kun, Mao, Xian-Ling, and Huang, Heyan
- Subjects
MACHINE learning ,DIRICHLET forms ,GIBBS sampling ,PERPLEXITY (Philosophy) ,SEMANTICS - Abstract
There is a mass of user-marked text data on the Internet, such as web pages with categories, papers with corresponding keywords, and tweets with hashtags. In recent years, supervised topic models, such as Labeled Latent Dirichlet Allocation, have been widely used to discover the abstract topics in labeled text corpora. However, none of these topic models have taken into consideration word order under the bag-of-words assumption, which will obviously lose a lot of semantic information. In this paper, in order to synchronously model semantical label information and word order, we propose a novel topic model, called Labeled Phrase Latent Dirichlet Allocation (LPLDA), which regards each document as a mixture of phrases and partly considers the word order. In order to obtain the parameter estimation for the proposed LPLDA model, we develop a batch inference algorithm based on Gibbs sampling technique. Moreover, to accelerate the LPLDA’s processing speed for large-scale stream data, we further propose an online inference algorithm for LPLDA. Extensive experiments were conducted among LPLDA and four state-of-the-art baselines. The results show (1) batch LPLDA significantly outperforms baselines in terms of case study, perplexity and scalability, and the third party task in most cases; (2) the online algorithm for LPLDA is obviously more efficient than batch method under the premise of good results. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
4. Collaborative representation analysis methods for feature extraction.
- Author
-
Hua, Juliang, Wang, Huan, Ren, Mingu, and Huang, Heyan
- Subjects
PATTERN recognition systems ,MACHINE learning ,CLASSIFICATION algorithms ,FEATURE extraction ,KERNEL (Mathematics) - Abstract
Recently, sparse representation (SR) theory gets much success in the fields of pattern recognition and machine learning. Many researchers use SR to design classification methods and dictionary learning via reconstruction residual. It was shown that collaborative representation (CR) is the key part in sparse representation-based classification (SRC) and collaborative representation-based classification (CRC). Both SRC and CRC are good classification methods. Here, we give a collaborative representation analysis (CRA) method for feature extraction. Not like SRC-/CRC-based methods (e.g., SPP and CRP), CRA could directly extract the features like PCA and LDA. Further, a Kernel CRA (KCRA) is developed via kernel tricks. The experimental results on FERET and AR face databases show that CRA and KCRA are two effective feature extraction methods and could get good performance. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
5. Food recommendation with graph convolutional network.
- Author
-
Gao, Xiaoyan, Feng, Fuli, Huang, Heyan, Mao, Xian-Ling, Lan, Tian, and Chi, Zewen
- Subjects
- *
FOOD preferences , *MACHINE learning - Abstract
Food recommendation has attracted increasing attentions to various food-related applications and services. The food recommender models aim to match users' preferences with recipes, where the key lies in the representation learning of users and recipes. However, ranging from early content-based filtering and collaborative filtering methods to recent hybrid methods, the existing work overlooks the various food-related relations, especially the ingredient-ingredient relations, leading to incomprehensive representations. To bridge this gap, we propose a novel model Food recommendation with Graph Convolutional Network (FGCN), which exploits ingredient-ingredient, ingredient-recipe, and recipe-user relations deeply. FGCN employs the information propagation mechanism and adopts multiple embedding propagation layers to model high-order connectivity across different food-related relations and enhance the representations. Specifically, we develop three types of information propagation: (1) ingredient-ingredient information propagation, (2) ingredient-recipe information propagation, and (3) recipe-user information propagation. To validate the effectiveness and rationality of FGCN, we conduct extensive experiments on a real-world dataset. The results show that the proposed FGCN outperforms the state-of-the-art baselines. Further in-depth analyses reveal that FGCN could alleviate the sparsity issue in food recommendation. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
6. Classifier-adaptation knowledge distillation framework for relation extraction and event detection with imbalanced data.
- Author
-
Song, Dandan, Xu, Jing, Pang, Jinhui, and Huang, Heyan
- Subjects
- *
MACHINE learning , *DATA mining , *BENEFIT performances , *IDENTIFICATION cards - Abstract
Fundamental information extraction tasks, such as relation extraction and event detection, suffer from a data imbalance problem. To alleviate this problem, existing methods rely mostly on well-designed loss functions to reduce the negative influence of imbalanced data. However, this approach requires additional hyper-parameters and limits scalability. Furthermore, these methods can only benefit specific tasks and do not provide a unified framework across relation extraction and event detection. In this paper, a Classifier-Adaptation Knowledge Distillation (CAKD) framework is proposed to address these issues, thus improving relation extraction and event detection performance. The first step is to exploit sentence-level identification information across relation extraction and event detection, which can reduce identification errors caused by the data imbalance problem without relying on additional hyper-parameters. Moreover, this sentence-level identification information is used by a teacher network to guide the baseline model's training by sharing its classifier. Like an instructor, the classifier improves the baseline model's ability to extract this sentence-level identification information from raw texts, thus benefiting overall performance. Experiments were conducted on both relation extraction and event detection using the Text Analysis Conference Relation Extraction Dataset (TACRED) and Automatic Content Extraction (ACE) 2005 English datasets, respectively. The results demonstrate the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
7. Deep kernel supervised hashing for node classification in structural networks.
- Author
-
Guo, Jia-Nan, Mao, Xian-Ling, Lin, Shu-Yang, Wei, Wei, and Huang, Heyan
- Subjects
- *
HILBERT space , *INFORMATION networks , *MACHINE learning - Abstract
Node classification in structural networks is a longstanding important problem in many real-world applications. Recent studies have shown that network embedding can greatly facilitate node classification by employing embedding algorithms to learn feature representations of nodes. Despite of promising performance, existing network embedding based methods are hard to capture the actual category features of a node because of the linearly inseparable problem in low-dimensional space; meanwhile they cannot incorporate both network structure information and node labels information into the representations simultaneously. To address the above problems, this paper presents a novel Deep Kernel Supervised Hashing (DKSH) method to learn hashing representations of nodes for node classification. Specifically, a deep multiple kernel learning is first employed to map nodes into suitable Hilbert space to deal with linearly inseparable problem. Then, instead of only considering structural similarity between two nodes, a novel similarity matrix is designed to merge both network structure information and node labels information. Supervised by the similarity matrix, the learned hashing representations can preserve the two kinds of information simultaneously from the learned Hilbert space. Extensive experiments show that the proposed method significantly outperforms the state-of-the-art baselines over three real-world benchmark datasets. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
8. Tag Expansion Using Friendship Information: Services for Picking-a-crowd for Crowdsourcing
- Author
-
Liang, Bin, Liu, Yiqun, Zhang, Min, Ma, Shaoping, Ru, Liyun, Zhang, Kuo, Junqueira Barbosa, Simone Diniz, Series editor, Chen, Phoebe, Series editor, Cuzzocrea, Alfredo, Series editor, Du, Xiaoyong, Series editor, Filipe, Joaquim, Series editor, Kara, Orhun, Series editor, Kotenko, Igor, Series editor, Sivalingam, Krishna M., Series editor, Ślęzak, Dominik, Series editor, Washio, Takashi, Series editor, Yang, Xiaokang, Series editor, Huang, Heyan, editor, Liu, Ting, editor, Zhang, Hua-Ping, editor, and Tang, Jie, editor
- Published
- 2014
- Full Text
- View/download PDF
9. Personality Prediction Based on All Characters of User Social Media Information
- Author
-
Wan, Danlin, Zhang, Chuang, Wu, Ming, An, Zhixiang, Junqueira Barbosa, Simone Diniz, Series editor, Chen, Phoebe, Series editor, Cuzzocrea, Alfredo, Series editor, Du, Xiaoyong, Series editor, Filipe, Joaquim, Series editor, Kara, Orhun, Series editor, Kotenko, Igor, Series editor, Sivalingam, Krishna M., Series editor, Ślęzak, Dominik, Series editor, Washio, Takashi, Series editor, Yang, Xiaokang, Series editor, Huang, Heyan, editor, Liu, Ting, editor, Zhang, Hua-Ping, editor, and Tang, Jie, editor
- Published
- 2014
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.