Jindian Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jindian Su has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Da Luo
College of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, China
2 shared publications - Jiebin Huang
South China University of Technology
2 shared publications - Shanshan Yu
College of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou 510640, China and Guangdong Province Precise Medicine and Big Data Engineering Technology Research Center for Traditional Chinese Medicine, Guangdong Pharmaceutical University, Guangzhou 510640, China
2 shared publications - Xianyu Guo
South China University of Technology
2 shared publications Xugang Zhou
South China University of Technology, Guangdong, China
2 shared publicationsDandan Ma
Guangdong Unicomm
1 shared publication
Latest Publications
- 12 July 2026
- Published by Springer Nature
- p. 562-574
ASSC: Adaptive Spatio-Semantic Calibration for Efficient New Intent Discovery
- 12 July 2026
- Published by Springer Nature
- p. 562-574
ASSC: Adaptive Spatio-Semantic Calibration for Efficient New Intent Discovery
- 9 June 2026
- Published by Springer Nature
- p. 407-418
SAGE: Semantic Alignment and Geometric Enhancement for Efficient Few-Shot Intent Detection
- 9 June 2026
- Published by Springer Nature
- p. 407-418
SAGE: Semantic Alignment and Geometric Enhancement for Efficient Few-Shot Intent Detection
- Open Access
- 16 October 2024
- Published by IOS Press
- p. 2798-2805
DINEX: Interpretable NLP via Diversified Natural Language Explanations
Natural Language Explanations (NLE) are becoming increasingly important in Interpretable Natural Language Processing, which can clarify the reasoning process and improve performance. It is essential to utilize human-authored gold explanations to improve the quality of explanations produced by the generator. However, the gold standard explanations within the same dataset are produced by a fixed group of annotators, leading to a more homogeneous perspective and style. This has inspired us to improve the quality of generated explanations by enhancing the diversity of the training set. Based on this, we introduce DINEX, a two-stage framework comprising a diversified explanation generator and an explanation-aware predictor, suitable for any task related to NLE. The first stage of DINEX augments the generator’s training set through two approaches: Semantic Similarity Sampling (SSS) and Structural Variety Generation (SVG). This enables the generator to learn how to produce NLE from diverse perspectives and styles. In the second stage, DINEX improves the predictor’s ability to capture the complementary semantics between contexts and explanations. It also reduces the impact of noise on predictions through dynamic perturbations. We conduct experiments on four datasets in the domains of Question Answering and Reasoning. The results show that DINEX achieves an average performance improvement of 5.49%, establishing a new state-of-the-art on the ComVE dataset. Evaluations by human evaluators and Large Language Models (LLMs) demonstrate that DINEX-generated explanations surpass the baseline in quality across 62.4% of the test samples.
- 16 October 2024
- Published by IOS Press
- p. 2798-2805
Open AccessDINEX: Interpretable NLP via Diversified Natural Language Explanations
Natural Language Explanations (NLE) are becoming increasingly important in Interpretable Natural Language Processing, which can clarify the reasoning process and improve performance. It is essential to utilize human-authored gold explanations to improve the quality of explanations produced by the generator. However, the gold standard explanations within the same dataset are produced by a fixed group of annotators, leading to a more homogeneous perspective and style. This has inspired us to improve the quality of generated explanations by enhancing the diversity of the training set. Based on this, we introduce DINEX, a two-stage framework comprising a diversified explanation generator and an explanation-aware predictor, suitable for any task related to NLE. The first stage of DINEX augments the generator’s training set through two approaches: Semantic Similarity Sampling (SSS) and Structural Variety Generation (SVG). This enables the generator to learn how to produce NLE from diverse perspectives and styles. In the second stage, DINEX improves the predictor’s ability to capture the complementary semantics between contexts and explanations. It also reduces the impact of noise on predictions through dynamic perturbations. We conduct experiments on four datasets in the domains of Question Answering and Reasoning. The results show that DINEX achieves an average performance improvement of 5.49%, establishing a new state-of-the-art on the ComVE dataset. Evaluations by human evaluators and Large Language Models (LLMs) demonstrate that DINEX-generated explanations surpass the baseline in quality across 62.4% of the test samples.
- 1 August 2024
- Published by Springer Nature
- p. 171-183
Enhancing Image Captioning with Transformer-Based Two-Pass Decoding Framework
- 1 August 2024
- Published by Springer Nature
- p. 171-183
Enhancing Image Captioning with Transformer-Based Two-Pass Decoding Framework
- 8 October 2023
- Published by Springer Nature
- p. 485-497
ASKSpell: Adaptive Surface Knowledge Enhances Tokens’ Semantic Representations for Chinese Spelling Check
- 8 October 2023
- Published by Springer Nature
- p. 485-497
ASKSpell: Adaptive Surface Knowledge Enhances Tokens’ Semantic Representations for Chinese Spelling Check
- 6 May 2021
- Published by Springer Nature
- p. 93-105
Improving Relation Extraction Using Semantic Role and Multi-task Learning
- 6 May 2021
- Published by Springer Nature
- p. 93-105
Improving Relation Extraction Using Semantic Role and Multi-task Learning
- Open Access
- 26 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 100551-100561
Enhancing Aspect-Based Sentiment Analysis With Capsule Network
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 and the aspect (or category), thus heavily depending on the quality of word embeddings and task-specific architectures. Although the recently pre-trained language models, i.e., BERT and XLNet, have achieved state-of-the-art performance in a variety of natural language processing (NLP) tasks, they still subject to the aspect-specific, local feature-aware and task-agnostic challenges. To address these challenges, this paper proposes a XLNet and capsule network based model XLNetCN for ABSA. XLNetCN firstly constructs auxiliary sentence to model the sequence-aspect relation and generate global aspect-specific representations, which enables to enhance aspect-awareness and ensure the full pre-training of XLNet for improving task-agnostic capability. 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, which are then merged with the global aspect-related representations for downstream classification via a softmax classifier. Experimental results show that XLNetCN outperforms significantly than the classical BERT, XLNet and traditional feature-based approaches on the two benchmark datasets of SemEval 2014, Laptop and Restaurant, and achieves new state-of-the-art results.
- 26 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 100551-100561
Open AccessEnhancing Aspect-Based Sentiment Analysis With Capsule Network
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 and the aspect (or category), thus heavily depending on the quality of word embeddings and task-specific architectures. Although the recently pre-trained language models, i.e., BERT and XLNet, have achieved state-of-the-art performance in a variety of natural language processing (NLP) tasks, they still subject to the aspect-specific, local feature-aware and task-agnostic challenges. To address these challenges, this paper proposes a XLNet and capsule network based model XLNetCN for ABSA. XLNetCN firstly constructs auxiliary sentence to model the sequence-aspect relation and generate global aspect-specific representations, which enables to enhance aspect-awareness and ensure the full pre-training of XLNet for improving task-agnostic capability. 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, which are then merged with the global aspect-related representations for downstream classification via a softmax classifier. Experimental results show that XLNetCN outperforms significantly than the classical BERT, XLNet and traditional feature-based approaches on the two benchmark datasets of SemEval 2014, Laptop and Restaurant, and achieves new state-of-the-art results.
- Open Access
- 18 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 176600-176612
Improving BERT-Based Text Classification With Auxiliary Sentence and Domain Knowledge
General language model BERT pre-trained on cross-domain text corpus, BookCorpus and Wikipedia, achieves excellent performance on a couple of natural language processing tasks through the way of fine-tuning in the downstream tasks. But it still lacks of task-specific knowledge and domain-related knowledge for further improving the performance of BERT model and more detailed fine-tuning strategy analyses are necessary. To address these problem, a BERT-based text classification model BERT4TC is proposed via constructing auxiliary sentence to turn the classification task into a binary sentence-pair one, aiming to address the limited training data problem and task-awareness problem. The architecture and implementation details of BERT4TC are also presented, as well as a post-training approach for addressing the domain challenge of BERT. Finally, extensive experiments are conducted on seven public widely-studied datasets for analyzing the fine-tuning strategies from the perspectives of learning rate, sequence length and hidden state vector selection. After that, BERT4TC models with different auxiliary sentences and post-training objectives are compared and analyzed in depth. The experiment results show that BERT4TC with suitable auxiliary sentence significantly outperforms both typical feature-based methods and fine-tuning methods, and achieves new state-of-the-art performance on multi-class classification datasets. For binary sentiment classification datasets, our BERT4TC post-trained with suitable domain-related corpus also achieves better results compared with original BERT model.
- 18 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 176600-176612
Open AccessImproving BERT-Based Text Classification With Auxiliary Sentence and Domain Knowledge
General language model BERT pre-trained on cross-domain text corpus, BookCorpus and Wikipedia, achieves excellent performance on a couple of natural language processing tasks through the way of fine-tuning in the downstream tasks. But it still lacks of task-specific knowledge and domain-related knowledge for further improving the performance of BERT model and more detailed fine-tuning strategy analyses are necessary. To address these problem, a BERT-based text classification model BERT4TC is proposed via constructing auxiliary sentence to turn the classification task into a binary sentence-pair one, aiming to address the limited training data problem and task-awareness problem. The architecture and implementation details of BERT4TC are also presented, as well as a post-training approach for addressing the domain challenge of BERT. Finally, extensive experiments are conducted on seven public widely-studied datasets for analyzing the fine-tuning strategies from the perspectives of learning rate, sequence length and hidden state vector selection. After that, BERT4TC models with different auxiliary sentences and post-training objectives are compared and analyzed in depth. The experiment results show that BERT4TC with suitable auxiliary sentence significantly outperforms both typical feature-based methods and fine-tuning methods, and achieves new state-of-the-art performance on multi-class classification datasets. For binary sentiment classification datasets, our BERT4TC post-trained with suitable domain-related corpus also achieves better results compared with original BERT model.
- Open Access
- 27 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 91160-91168
Improving Distantly Supervised Relation Classification With Attention and Semantic Weight
Distantly supervised relation classification aims at identifying the relationship between two given entities and plays an essential part in Natural Language Processing. Although distant supervision is able to generate labeled data automatically, it is facing with the problem of noisy data due to the wrong labeling problems. The attention mechanism is one of the most popular methods to reduce the influence of mislabeled data. However, regardless of the correlation among relations, most existing methods treat all relationships as independent classes. In general, the definitions of relations contain rich semantic information, which improves the performance of the model, especially when classifying long-tail relations which lacks of training data. Based on this idea, we propose a novel neural network architecture with an attention mechanism in the paper. First, we use bidirectional GRU to encode relation definitions as the context representations of relations. Then we use the merge attention mechanism to make full use of the hidden states obtained by GRU. To help the model make full use of the context of the entities, we also introduce semantic weights, calculated by the length of the shortest path between entities and words in the dependency tree. We conduct experiments on the widely used New York Times relation extraction corpus, and the results demonstrate that our model outperforms most of the state-of-the-art models.
- 27 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 91160-91168
Open AccessImproving Distantly Supervised Relation Classification With Attention and Semantic Weight
Distantly supervised relation classification aims at identifying the relationship between two given entities and plays an essential part in Natural Language Processing. Although distant supervision is able to generate labeled data automatically, it is facing with the problem of noisy data due to the wrong labeling problems. The attention mechanism is one of the most popular methods to reduce the influence of mislabeled data. However, regardless of the correlation among relations, most existing methods treat all relationships as independent classes. In general, the definitions of relations contain rich semantic information, which improves the performance of the model, especially when classifying long-tail relations which lacks of training data. Based on this idea, we propose a novel neural network architecture with an attention mechanism in the paper. First, we use bidirectional GRU to encode relation definitions as the context representations of relations. Then we use the merge attention mechanism to make full use of the hidden states obtained by GRU. To help the model make full use of the context of the entities, we also introduce semantic weights, calculated by the length of the shortest path between entities and words in the dependency tree. We conduct experiments on the widely used New York Times relation extraction corpus, and the results demonstrate that our model outperforms most of the state-of-the-art models.
- 14 August 2018
- Published by Springer Nature
- p. 391-403
Dependency Parsing and Attention Network for Aspect-Level Sentiment Classification
- 14 August 2018
- Published by Springer Nature
- p. 391-403
Dependency Parsing and Attention Network for Aspect-Level Sentiment Classification