Haibin Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Haibin Chen has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Qianli Ma
South China University of Technology, Guangzhou, China
3 shared publications - Bo Zheng
Alibaba Group, Hangzhou, China
2 shared publications - Jiangyue Yan
South China Univ Technol, Sch Comp Sci & Engn, Guangzhou 510006, Peoples R China
2 shared publications - Langming Liu
Taobao & Tmall Group of Alibaba, Hangzhou, China
2 shared publications - Liuhong Yu
South China Univ Technol, Sch Comp Sci & Engn, Guangzhou 510006, Peoples R China
2 shared publications - Shilei Liu
Taobao & Tmall Group of Alibaba, Hangzhou, China
2 shared publications
Latest Publications
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6461-6465
ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6461-6465
Open AccessECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5311-5321
ChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5311-5321
Open AccessChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models
- 1 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 276-285
Does the Order Matter? A Random Generative Way to Learn Label Hierarchy for Hierarchical Text Classification
Hierarchical Text Classification (HTC) is an essential and challenging task due to the difficulty of modeling label hierarchy. Recent generative methods have achieved state-of-the-art performance by flattening the local label hierarchy into a label sequence with a specific order. However, the order between labels does not naturally exist and the generation of the current label should incorporate the information in all other target labels. Moreover, the generative methods usually suffer from the error accumulation problem. To this end, we propose a new framework named sequence-to-label (Seq2Label) with a random generative way to learn label hierarchy for hierarchical text classification. Instead of using only one specific order, we shuffle the label sequence by a Label Sequence Random Shuffling (LSRS) mechanism so that a text will be mapped to several different order label sequences during the training phase. To alleviate the error accumulation problem, we further propose a Hierarchy-aware Negative Sampling (HNS) strategy with a negative label-aware loss to better distinguish target labels and negative labels. In this way, our model can capture the hierarchical and co-occurrence information of the target labels of each text. The experimental results on three benchmark datasets show that Seq2Label achieves state-of-the-art results.
- 1 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 276-285
Does the Order Matter? A Random Generative Way to Learn Label Hierarchy for Hierarchical Text Classification
Hierarchical Text Classification (HTC) is an essential and challenging task due to the difficulty of modeling label hierarchy. Recent generative methods have achieved state-of-the-art performance by flattening the local label hierarchy into a label sequence with a specific order. However, the order between labels does not naturally exist and the generation of the current label should incorporate the information in all other target labels. Moreover, the generative methods usually suffer from the error accumulation problem. To this end, we propose a new framework named sequence-to-label (Seq2Label) with a random generative way to learn label hierarchy for hierarchical text classification. Instead of using only one specific order, we shuffle the label sequence by a Label Sequence Random Shuffling (LSRS) mechanism so that a text will be mapped to several different order label sequences during the training phase. To alleviate the error accumulation problem, we further propose a Hierarchy-aware Negative Sampling (HNS) strategy with a negative label-aware loss to better distinguish target labels and negative labels. In this way, our model can capture the hierarchical and co-occurrence information of the target labels of each text. The experimental results on three benchmark datasets show that Seq2Label achieves state-of-the-art results.
- 11 April 2023
- Published by Elsevier in Information Sciences
- Vol. 637
Sequence labeling with MLTA: Multi-level topic-aware mechanism
- 11 April 2023
- Published by Elsevier in Information Sciences
- Vol. 637
Sequence labeling with MLTA: Multi-level topic-aware mechanism
- 26 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 29 (23299290) , 2048-2057
Corpus-Aware Graph Aggregation Network for Sequence Labeling
Current state-of-the-art sequence labeling models are typically based on sequential architecture such as Bi-directional LSTM (BiLSTM). However, the structure of processing a word at a time based on the sequential order restricts the full utilization of non-sequential features, including syntactic relationships, word co-occurrence relations, and document topics. They can be regarded as the corpus-level features and critical for sequence labeling. In this paper, we propose a Corpus-Aware Graph Aggregation Network. Specifically, we build three types of graphs, i.e., a word-topic graph, a word co-occurrence graph, and a word syntactic dependency graph, to express different kinds of corpus-level non-sequential features. After that, a graph convolutional network (GCN) is adapted to model the relations between words and non-sequential features. Finally, we employ a label-aware attention mechanism to aggregate corpus-aware non-sequential features and sequential ones for sequence labeling. The experimental results on four sequence labeling tasks (named entity recognition, chunking, multilingual sequence labeling, and target-based sentiment analysis) show that our model achieves state-of-the-art performance.
- 26 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 29 (23299290) , 2048-2057
Corpus-Aware Graph Aggregation Network for Sequence Labeling
Current state-of-the-art sequence labeling models are typically based on sequential architecture such as Bi-directional LSTM (BiLSTM). However, the structure of processing a word at a time based on the sequential order restricts the full utilization of non-sequential features, including syntactic relationships, word co-occurrence relations, and document topics. They can be regarded as the corpus-level features and critical for sequence labeling. In this paper, we propose a Corpus-Aware Graph Aggregation Network. Specifically, we build three types of graphs, i.e., a word-topic graph, a word co-occurrence graph, and a word syntactic dependency graph, to express different kinds of corpus-level non-sequential features. After that, a graph convolutional network (GCN) is adapted to model the relations between words and non-sequential features. Finally, we employ a label-aware attention mechanism to aggregate corpus-aware non-sequential features and sequential ones for sequence labeling. The experimental results on four sequence labeling tasks (named entity recognition, chunking, multilingual sequence labeling, and target-based sentiment analysis) show that our model achieves state-of-the-art performance.