Social Email:
tongsw@mail.ustc.edu.cn
Github:
https://github.com/tswsxk
Contact:
Science and Technology Laboratory Building, Room 208
West Campus, USTC, Hefei, Anhui, China, 230027.
Shiwei Tong
Published Papers
[1] Incremental Cognitive Diagnosis for Intelligent Education Shiwei Tong, Jiayu Liu, Yuting Hong, Zhenya Huang, Le Wu, Qi Liu, Wei Huang, Enhong Chen, Dan Zhang
{KDD} '22: The 28th {ACM} {SIGKDD} Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14 - 18, 2022, 2022, 1760--1770.
Cognitive diagnosis, aiming at providing an approach to reveal the proficiency level of learners on knowledge concepts, plays an important role in intelligent education area and has recently received more and more attention. Although a number of works have been proposed in recent years, most of contemporary works acquire the traits parameters of learners and items in a transductive way, which are only suitable for stationary data. However, in the real scenario, the data is collected online, where learners, test items and interactions usually grow continuously, which can rarely meet the stationary condition. To this end, we propose a novel framework, Incremental Cognitive Diagnosis (ICD), to tailor cognitive diagnosis into the online scenario of intelligent education. Specifically, we first design a Deep Trait Network (DTN), which acquires the trait parameters in an inductive way rather than a transductive way. Then, we propose an Incremental Update Algorithm (IUA) to balance the effectiveness and training efficiency. We carry out Turning Point (TP) analysis to reduce update frequency, where we derive the minimum update condition based on the monotonicity theory of cognitive diagnosis. Meanwhile, we use a momentum update strategy on the incremental data to decrease update time without sacrificing effectiveness. Moreover, to keep the trait parameters as stable as possible, we refine the loss function in the incremental updating stage. Last but no least, our ICD is a general framework which can be applied to most of contemporary cognitive diagnosis models. To the best of our knowledge, this is the first attempt to investigate the incremental cognitive diagnosis problem with theoretical results about the update condition and a tailored incremental learning strategy. Extensive experiments demonstrate the effectiveness and robustness of our method.
@inproceedings{DBLP:conf/kdd/TongLHHWLHCZ22, author = {Tong, Shiwei and Liu, Jiayu and Hong, Yuting and Huang, Zhenya and Wu, Le and Liu, Qi and Huang, Wei and Chen, Enhong and Zhang, Dan}, editor = {Zhang, Aidong and Rangwala, Huzefa}, title = {Incremental Cognitive Diagnosis for Intelligent Education}, booktitle = {{KDD} '22: The 28th {ACM} {SIGKDD} Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14 - 18, 2022}, pages = {1760--1770}, publisher = {{ACM}}, year = {2022}, url = {https://doi.org/10.1145/3534678.3539399}, doi = {10.1145/3534678.3539399}, timestamp = {Fri, 11 Nov 2022 09:36:56 +0100}, biburl = {https://dblp.org/rec/conf/kdd/TongLHHWLHCZ22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
[2] Item Response Ranking for Cognitive Diagnosis Shiwei Tong, Qi Liu, Runlong Yu, Wei Huang, Zhenya Huang, Pardos Zarchary, Weijie Jiang
Inproceedings of 30th International Joint Conference on Artificial Intelligence (IJCAI'21), Montreal-themed Virtual Reality, 2021.
Cognitive diagnosis, a fundamental task in education area, aims at providing an approach to reveal the proficiency level of students on knowledge concepts. Actually, monotonicity is one of the basic conditions in cognitive diagnosis theory, which assumes that student's proficiency is monotonic with the probability of giving the right response to a test item. However, few of previous methods consider the monotonicity during optimization. To this end, we propose Item Response Ranking framework (IRR), aiming at introducing pairwise learning into cognitive diagnosis to well model the monotonicity between item responses. Specifically, we first use an item specific sampling method to sample item responses and construct response pairs based on their partial order, where we propose the two-branch sampling methods to handle the unobserved responses. After that, we use a pairwise objective function to exploit the monotonicity in the pair formulation. In fact, IRR is a general framework which can be applied to most of contemporary cognitive diagnosis models. Extensive experiments demonstrate the effectiveness and interpretability of our method.
@inproceedings{tong2021item, author = {Tong, Shiwei and Liu, Qi and Yu, Runlong and Huang, Wei and Huang, Zhenya and Zarchary, Pardos and Jiang, Weijie}, title = {Item Response Ranking for Cognitive Diagnosis}, booktitle = {Inproceedings of 30th International Joint Conference on Artificial Intelligence}, year = {2021} }
Knowledge Tracing (KT) is a fundamental but challenging task in online education that traces learners' evolving knowledge states. Much attention has been drawn to this area and several works such as Bayesian and Deep Knowledge Tracing have been proposed. Recent works have explored the value of relations among concepts and proposed to introduce knowledge structure into KT tasks. However, the propagated influence among concepts, which has been shown to be a key factor in human learning by the educational theories, is still under-explored. In this paper, we propose a new framework called Structure-based Knowledge Tracing (SKT), which exploits the multiple relations in knowledge structure to model the influence propagation among concepts. In the SKT framework, we consider both the temporal effect on the exercising sequence and the spatial effect on the knowledge structure. We take advantages of two novel formulations in modeling the influence propagation on the knowledge structure with multiple relations. For undirected relations such as similarity relations, the synchronization propagation method is adopted, where the influence propagates bidirectionally between neighbor concepts. For directed relations such as prerequisite relations, the partial propagation method is applied, where the influence can only unidirectionally propagate from a predecessor to a successor. Meanwhile, we employ the gated functions to update the states of concepts temporally and spatially. We demonstrate the effectiveness and interpretability of SKT with extensive experiments.
@inproceedings{tong2020structure, author = {Tong, Shiwei and Liu, Qi and Huang, Wei and Huang, Zhenya and Chen, Enhong and Liu, Chuanren and Ma, Haiping and Wang, Shijin}, title = {Structure-based Knowledge Tracing: An Influence Propagation View}, booktitle = {2020 IEEE International Conference on Data Mining (ICDM)}, pages = {541--550}, year = {2020}, organization = {IEEE} }
[4] Exploiting cognitive structure for adaptive learning
Qi Liu, Shiwei Tong, Chuanren Liu, Hongke Zhao, Enhong Chen, Haiping Ma, Shijin Wang
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'19), Anchorage, Alaska, USA, 2019, 627--635.
Adaptive learning, also known as adaptive teaching, relies on learning path recommendation, which sequentially recommends personalized learning items (e.g., lectures, exercises) to satisfy the unique needs of each learner. Although it is well known that modeling the cognitive structure including knowledge level of learners and knowledge structure (e.g., the prerequisite relations) of learning items is important for learning path recommendation, existing methods for adaptive learning often separately focus on either knowledge levels of learners or knowledge structure of learning items. To fully exploit the multifaceted cognitive structure for learning path recommendation, in this paper, we propose a Cognitive Structure Enhanced framework Adaptive Learning, named CSEAL. By viewing path recommendation as a Markov Decision Process (MDP) and applying an actor-critic algorithm, our framework can sequentially identify the right learning items to different learners. Specifically, we first utilize a recurrent neural network to trace the evolving knowledge levels of learners at each learning step. Then, we design a navigation algorithm on knowledge graph to ensure the logicality of learning paths, which can also reduce the search space in the decision process. Finally, the actor-critic algorithm is used to determine what to learn next, whose parameters are dynamically updated along the learning path. Extensive experiments with real-world data demonstrate the effectiveness and robustness of CSEAL in comparison with alternative approaches.
@inproceedings{liu2019exploiting, author = {Liu, Qi and Tong, Shiwei and Liu, Chuanren and Zhao, Hongke and Chen, Enhong and Ma, Haiping and Wang, Shijin}, title = {Exploiting cognitive structure for adaptive learning}, booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}, pages = {627--635}, year = {2019} }
[5] Tipster: A Topic-Guided Language Model for Topic-Aware Text Segmentation
Zheng Gong, Shiwei Tong, Han Wu, Qi Liu, Hanqing Tao, Wei Huang, Runlong Yu
Database Systems for Advanced Applications: 27th International Conference, DASFAA 2022, Virtual Event, April 11–14, 2022, Proceedings, Part III, Berlin, Heidelberg, 2022, 213–221.
The accurate segmentation and structural topics of plain documents not only meet people’s reading habit, but also facilitate various downstream tasks. Recently, some works have consistently given positive hints that text segmentation and segment topic labeling could be regarded as a mutual task, and cooperating with word distributions has the potential to model latent topics in a certain document better. To this end, we present a novel model namely Tipster to solve text segmentation and segment topic labeling collaboratively. We first utilize a neural topic model to infer latent topic distributions of sentences considering word distributions. Then, our model divides the document into topically coherent segments based on the topic-guided contextual sentence representations of the pre-trained language model and assign relevant topic labels to each segment. Finally, we conduct extensive experiments which demonstrate that Tipster achieves the state-of-the-art performance in both text segmentation and segment topic labeling tasks.
@inproceedings{10.1007/978-3-031-00129-1_14, author = {Gong, Zheng and Tong, Shiwei and Wu, Han and Liu, Qi and Tao, Hanqing and Huang, Wei and Yu, Runlong}, title = {Tipster: A Topic-Guided Language Model for Topic-Aware Text Segmentation}, year = {2022}, isbn = {978-3-031-00128-4}, publisher = {Springer-Verlag}, url = {https://doi.org/10.1007/978-3-031-00129-1\_14}, doi = {10.1007/978-3-031-00129-1\_14}, booktitle = {Database Systems for Advanced Applications: 27th International Conference, DASFAA 2022, Virtual Event, April 11–14, 2022, Proceedings, Part III}, pages = {213–221}, numpages = {9}, keywords = {Text segmentation, Neural topic model, Language model} }
Cognitive psychology research shows that humans have the instinct for abstract thinking, where association plays an essential role in language comprehension. Especially for Chinese, its ideographic writing system allows radicals to trigger semantic association without the need of phonetics. In fact, subconsciously using the associative information guided by radicals is a key for readers to ensure the robustness of semantic understanding. Fortunately, many basic and extended concepts related to radicals are systematically included in Chinese language dictionaries, which leaves a handy but unexplored way for improving Chinese text representation and classification. To this end, we draw inspirations from cognitive principles between ideography and human associative behavior to propose a novel Radical-guided Associative Model (RAM) for Chinese text classification. RAM comprises two coupled spaces, namely Literal Space and Associative Space, which imitates the real process in people's mind when understanding a Chinese text. To be specific, we first devise a serialized modeling structure in Literal Space to thoroughly capture the sequential information of Chinese text. Then, based on the authoritative information provided by Chinese language dictionaries, we design an association module and put forward a strategy called Radical-Word Association to use ideographic radicals as the medium to associate prior concept words in Associative Space. Afterwards, we design an attention module to imitate people's matching and decision between Literal Space and Associative Space, which can balance the importance of each associative words under specific contexts. Finally, extensive experiments on two real-world datasets prove the effectiveness and rationality of RAM, with good cognitive insights for future language modeling.
@inproceedings{tao2021ideography, author = {Tao, Hanqing and Tong, Shiwei and Zhang, Kun and Xu, Tong and Liu, Qi and Chen, Enhong and Hou, Min}, title = {Ideography Leads Us to the Field of Cognition: A Radical-Guided Associative Model for Chinese Text Classification}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, volume = {35}, number = {15}, pages = {13898--13906}, year = {2021} }
Representation learning of examination papers is the cornerstone of the Examination Paper Analysis (EPA) in education area including Paper Difficulty Prediction (PDR) and Finding Similar Papers (FSP). Previous works mainly focus on the representation learning of each test item, but few works notice the hierarchical document structure in examination papers. To this end, in this paper, we propose a novel Examination Organization Encoder (EOE) to learn a robust representation of the examination paper with the hierarchical document structure. Specifically, we first propose a syntax parser to recover the hierarchical document structure and convert an examination paper to an Examination Organization Tree (EOT), where the test items are the leaf nodes and the internal nodes are summarization of their child nodes. Then, we applied a two-layer GRU-based module to obtain the representation of each leaf node. After that, we design a subtree encoder module to aggregate the representation of each leaf node, which is used to calculate an embedding for each layer in the EOT. Finally, we feed all the layer embedding into an output module, the process is over and we get the examination paper representation that can be used for downstream tasks. Extensive experiments on real-world data demonstrate the effectiveness and interpretability of our method.
@inproceedings{ma2021enhanced, author = {Ma, Yixiao and Tong, Shiwei and Liu, Ye and Wu, Likang and Liu, Qi and Chen, Enhong and Tong, Wei and Yan, Zi}, title = {Enhanced Representation Learning for Examination Papers with Hierarchical Document Structure}, booktitle = {Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval}, pages = {2156--2160}, year = {2021} }
In education systems, Finding Similar Exercises (FSE) is the key step for both exercise retrieval and duplicate detection. Recently, more and more attention has been drawn into this area and several works have been proposed, to utilize the exercise content (e.g., texts or images) or the labeled knowledge concepts. Such approaches, however, have failed to take knowledge hierarchy into account. To this end, we advance a novel knowledge-aware multimodal network, namely KnowNet, for finding similar exercises in large-scale online education systems by integrating the knowledge hierarchy into the heterogeneous exercise data and learning a relation-aware semantic representation. Specifically, we first propose a Content Representation Layer (CRL) to learn a unified semantic representation of the heterogeneous exercise content. Then, we design a Hierarchy Fusion Layer (HFL) to exploit the knowledge hierarchy. By combining the knowledge hierarchy, HFL can not only retrieve the relation-aware semantic representation but also provide an interpretable view to investigate the similarity of exercises. Finally, we adopt a Similarity Score Layer (SSL) for returning similar exercises. Extensive experiments demonstrate the effectiveness and interpretability of KnowNet.
@inproceedings{tong2020exploiting, author = {Tong, Wei and Tong, Shiwei and Huang, Wei and He, Liyang and Ma, Jianhui and Liu, Qi and Chen, Enhong}, title = {Exploiting Knowledge Hierarchy for Finding Similar Exercises in Online Education Systems}, booktitle = {2020 IEEE International Conference on Data Mining (ICDM)}, pages = {1298--1303}, year = {2020}, organization = {IEEE} }
Recent years, Chinese text classification has attracted more and more research attention. However, most existing techniques which specifically aim at English materials may lose effectiveness on this task due to the huge difference between Chinese and English. Actually, as a special kind of hieroglyphics, Chinese characters and radicals are semantically useful but still unexplored in the task of text classification. To that end, in this paper, we first analyze the motives of using multiple granularity features to represent a Chinese text by inspecting the characteristics of radicals, characters and words. For better representing the Chinese text and then implementing Chinese text classification, we propose a novel Radical-aware Attention-based Four-Granularity (RAFG) model to take full advantages of Chinese characters, words, character-level radicals, word-level radicals simultaneously. Specifically, RAFG applies a serialized BLSTM structure which is context-aware and able to capture the long-range information to model the character sharing property of Chinese and sequence characteristics in texts. Further, we design an attention mechanism to enhance the effects of radicals thus model the radical sharing property when integrating granularities. Finally, we conduct extensive experiments, where the experimental results not only show the superiority of our model, but also validate the effectiveness of radicals in the task of Chinese text classification
@inproceedings{tao2019radical, author = {Tao, Hanqing and Tong, Shiwei and Zhao, Hongke and Xu, Tong and Jin, Binbin and Liu, Qi}, title = {A radical-aware attention-based model for chinese text classification}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, volume = {33}, number = {01}, pages = {5125--5132}, year = {2019} }
Word embedding is a basic and very important topic in the field of Natural Language Processing. For Chinese, which has the nature of pictographic representation, it is urgent to explore more interpretable strategies to capture the language patterns in which morphological information is used to convey semantics. In this paper, we elaborate that Chinese word embeddings can be substantially enhanced by the morphological information hidden in characters which is reflected not only in strokes order sequentially, but also in character glyphs spatially. Then, we propose a novel Dual-channel Word Embedding model to realize the joint learning of sequential and spatial information of Chinese characters, so as to further enrich the representation of words. Through the evaluation on both word similarity and word analogy task, our model significantly outperforms other baseline methods and shows great interpretability.
@article{tao2019chinese, author = {Tao, Hanqing and Tong, Shiwei and Xu, Tong and Liu, Qi and Chen, Enhong}, title = {Chinese Embedding via Stroke and Glyph Information: A Dual-channel View}, journal = {JOURNAL OF CHINESE INFORMATION PROCESSING}, year = {2019} }
In intelligent education systems, question difficulty prediction (QDP) is a fundamental task of many applications, such as personalized question recommendation and test paper analysis. Previous work mainly focus on data-driven QDP methods, which are heavily relied on the large-scale labeled dataset of courses. To alleviate the labor intensity, an intuitive method is to introduce domain adaptation into QDP and consider each course as a domain. In educational psychology, there are two factors influencing difficulty common to different courses: the obstacles of comprehending the question and generating a response, namely stimulus and task difficulty. To this end, we propose a novel Stimulus and Task difficulty-based Adversarial Network (STAN) that models question difficulty from the views of stimulus and task. Then, in order to align the difficulty distribution of the source domain and the target domain, we utilize the conditional adversarial learning with readability-enhanced pseudo-labels. Meanwhile, we proposed a sampling method based on density estimation to implicit alignment. Finally, we conduct experiments on the real questions datasets to evaluate the effectiveness of our QDP model and domain adaptation method. Our method significantly improves accuracy over state-of-the-art methods on real-world question data of multiple courses.
@inproceedings{huang2021stan, author = {Huang, Ye and Huang, Wei and Tong, Shiwei and Huang, Zhenya and Liu, Qi and Chen, Enhong and Ma, Jianhui and Wan, Liang and Wang, Shijin}, title = {STAN: Adversarial Network for Cross-domain Question Difficulty Prediction}, booktitle = {2021 IEEE International Conference on Data Mining (ICDM)}, pages = {220--229}, year = {2021}, organization = {IEEE} }
In the online education system, predicting the knowledge of exercises is a fundamental task of many applications, such as cognitive diagnosis. Usually, experts consider this problem as Hierarchical Multi-label Classification (HMC), since the knowledge concepts exhibit a multi-level structure. However, existing methods either sacrificed knowledge consistency for classification accuracy or sacrificed classification accuracy for knowledge consistency. Maintaining the balance is difficult. To forgo this dilemma, in this paper, we develop a novel frame-work called Consistency-Aware Multi-modal Network (Cam-Net). Specifically, we develop a multi-modal embedding module to learn the representation of the multi-modal exercise. Then, we adopt a hybrid prediction method consisting of the flat prediction module and the local prediction module. The local prediction module deals with the relation between the knowledge hierarchy and the input exercise. The flat prediction module focuses on maintaining knowledge consistency. Finally, to balance classification accuracy and knowledge consistency, we combine the outputs of two modules to make a final prediction. Extensive experimental results on two real-world datasets demonstrate the high performance and the ability to reduce knowledge inconsistency of CamNet.
@inproceedings{lei2021consistency, author = {Lei, Siqi and Huang, Wei and Tong, Shiwei and Liu, Qi and Huang, Zhenya and Chen, Enhong and Su, Yu}, title = {Consistency-aware Multi-modal Network for Hierarchical Multi-label Classification in Online Education System}, booktitle = {2021 IEEE International Conference on Big Knowledge (ICBK)}, pages = {1--8}, year = {2021}, organization = {IEEE}, tag = {Best Student Paper} }
@inproceedings{DBLP:conf/sigir/TongWZTH022, author = {Tong, Hanshuang and Wang, Zhen and Zhou, Yun and Tong, Shiwei and Han, Wenyuan and Liu, Qi}, editor = {Amig{\'{o}}, Enrique and Castells, Pablo and Gonzalo, Julio and Carterette, Ben and Culpepper, J. Shane and Kazai, Gabriella}, title = {Introducing Problem Schema with Hierarchical Exercise Graph for Knowledge Tracing}, booktitle = {{SIGIR} '22: The 45th International {ACM} {SIGIR} Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11 - 15, 2022}, pages = {405--415}, publisher = {{ACM}}, year = {2022}, url = {https://doi.org/10.1145/3477495.3532004}, doi = {10.1145/3477495.3532004}, timestamp = {Sat, 09 Jul 2022 09:25:34 +0200}, biburl = {https://dblp.org/rec/conf/sigir/TongWZTH022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@ARTICLE{9770424, author = {Tao, Hanqing and Zhu, Guanqi and Chen, Enhong and Tong, Shiwei and Zhang, Kun and Xu, Tong and Liu, Qi and Ong, Yew-Soon}, journal = {IEEE Transactions on Knowledge and Data Engineering}, title = {Learning from Ideography and Labels: A Schema-aware Radical-guided Associative Model for Chinese Text Classification}, year = {2022}, volume = {}, number = {}, pages = {1-1}, doi = {10.1109/TKDE.2022.3171690} }
[15] Guided Attention Network for Concept Extraction
Songtao Fang, Zhenya Huang, Ming He, Shiwei Tong, Xiaoqing Huang, Ye Liu, Jie Huang, Qi Liu
Inproceedings of 30th International Joint Conference on Artificial Intelligence (IJCAI'21), Montreal-themed Virtual Reality, 2021.
Concept extraction aims to find words or phrases describing a concept from massive texts. Recently, researchers propose many neural network-based methods to automatically extract concepts. Although these methods for this task show promising results, they ignore structured information in the raw textual data (e.g., title, topic, and clue words). In this paper, we propose a novel model, named Guided Attention Concept Extraction Network (GACEN), which uses title, topic, and clue words as additional supervision to provide guidance directly. Specifically, GACEN comprises two attention networks, one of them is to gather the relevant title and topic information for each context word in the document. The other one aims to model the implicit connection between informative words (clue words) and concepts. Finally, we aggregate information from two networks as input to Conditional Random Field (CRF) to model dependencies in the output. We collected clue words for three well-studied datasets. Extensive experiments demonstrate that our model outperforms the baseline models with a large margin.
@article{fangguided, author = {Fang, Songtao and Huang, Zhenya and He, Ming and Tong, Shiwei and Huang, Xiaoqing and Liu, Ye and Huang, Jie and Liu, Qi}, title = {Guided Attention Network for Concept Extraction}, booktitle = {Inproceedings of 30th International Joint Conference on Artificial Intelligence}, year = {2021} }
Similar text search aims to find texts relevant to a given query from a database, which is fundamental in many information retrieval applications, such as question search and exercise search. Since millions of texts always exist behind practical search engine systems, a well-developed text search system usually consists of recall and ranking stages. Specifically, the recall stage serves as the basis in the system, where the main purpose is to find a small set of relevant candidates accurately and efficiently. Towards this goal, deep semantic hashing, which projects original texts into compact hash codes, can support good search performance. However, learning desired textual hash codes is extremely difficult due to the following problems. First, compact hash codes (with short length) can improve retrieval efficiency, but the demand for learning compact hash codes cannot guarantee accuracy due to severe information loss. Second, existing methods always learn the unevenly distributed codes in the space from a local perspective, leading to unsatisfactory code-balance results. Third, a large fraction of textual data contains various types of noise in real-world applications, which causes the deviation of semantics in hash codes. To this end, in this paper, we first propose a general unsupervised encoder-decoder semantic hashing framework, namely MASH (short for Memory-bAsed Semantic Hashing), to learn the balanced and compact hash codes for similar text search. Specifically, with a target of retaining semantic information as much as possible, the encoder introduces a novel relevance constraint among informative high-dimensional representations to guide the compact hash code learning. Then, we design an external memory where the hashing learning can be optimized in the global space to ensure the code balance of the learning results, which can promote search efficiency. Besides, to alleviate the performance degradation problem of the model caused by text noise, we propose an improved SMASH (short for denoiSing Memory-bAsed Semantic Hashing) model by incorporating a noise-aware encoder-decoder framework. This framework considers the noise degree for each text from the semantic deviation aspect, ensuring the robustness of hash codes. Finally, we conduct extensive experiments in three real-world datasets. The experimental results clearly demonstrate the effectiveness and efficiency of MASH and SMASH in generating balanced and compact hash codes, as well as the superior denoising ability of SMASH.
@article{10.1145/3570725, author = {He, Liyang and Huang, Zhenya and Chen, Enhong and Liu, Qi and Tong, Shiwei and Wang, Hao and Lian, Defu and Wang, Shijin}, title = {An Efficient and Robust Semantic Hashing Framework for Similar Text Search}, year = {2023}, publisher = {Association for Computing Machinery}, issn = {1046-8188}, url = {https://doi.org/10.1145/3570725}, doi = {10.1145/3570725}, note = {Just Accepted}, journal = {ACM Trans. Inf. Syst.}, month = {jan}, keywords = {Semantic Hashing, Similarity Search, Efficient Codes, Robust Codes} }
@ARTICLE{9894725, author = {Huang, Wei and Chen, Enhong and Liu, Qi and Xiong, Hui and Huang, Zhenya and Tong, Shiwei and Zhang, Dan}, journal = {IEEE Transactions on Knowledge and Data Engineering}, title = {HmcNet: A General Approach for Hierarchical Multi-Label Classification}, year = {2022}, volume = {}, number = {}, pages = {1-16}, doi = {10.1109/TKDE.2022.3207511} }
Patent
Enhong Chen, Qi Liu, Hanqing Tao, Shiwei Tong, Tong Xu.
Chinese text classification method and device based on radical association mechanism, public,
CN202011437069.2.
Wei Tong, Qi Liu, Enhong Chen, Shiwei Tong, Liyang He, Wei Huang.
Similar test question identification method based on knowledge structure, public,
CN202011125402.6.
Qi Liu, Enhong Chen, Shiwei Tong, Wei Huang, Wei Tong, Zhenya Huang, Ye Huang, Shijin Wang.
Knowledge tracking method based on heterogeneous structure, public,
CN202010355445.7.
Enhong Chen, Qi Liu, Tong Xu, Shiwei Tong, Hanqing Tao.
Morphological dual-channel Chinese word embedding method based on strokes and fonts, public,
CN201910881062.0.
Enhong Chen, Qi Liu, Tong Xu, Hanqing Tao, Shiwei Tong, Hongke Zhao, Binbin Jin.
A method and system for classifying Chinese texts, public,
CN201811371967.5.
Enhong Chen, Qi Liu, Binbin Jin, Hongke Zhao, Shiwei Tong.
Answer ordering method for community question-answer platform, licensing announcement,
CN201810186972.2.