Yinglong Ma

Mingjun Zhao, Mengzhen Wang, Yinglong Ma et al.

Text clustering, as one of the most fundamental challenges in unsupervised learning, aims at grouping semantically similar text segments without relying on human annotations. With the rapid development of deep learning, deep clustering has achieved significant advantages over traditional clustering methods. Despite the effectiveness, most existing deep text clustering methods rely heavily on representations pre-trained in general domains, which may not be the most suitable solution for clustering in specific target domains. To address this issue, we propose CEIL, a novel Classification-Enhanced Iterative Learning framework for short text clustering, which aims at generally promoting the clustering performance by introducing a classification objective to iteratively improve feature representations. In each iteration, we first adopt a language model to retrieve the initial text representations, from which the clustering results are collected using our proposed Category Disentangled Contrastive Clustering (CDCC) algorithm. After strict data filtering and aggregation processes, samples with clean category labels are retrieved, which serve as supervision information to update the language model with the classification objective via a prompt learning approach. Finally, the updated language model with improved representation ability is used to enhance clustering in the next iteration. Extensive experiments demonstrate that the CEIL framework significantly improves the clustering performance over iterations, and is generally effective on various clustering algorithms. Moreover, by incorporating CEIL on CDCC, we achieve the state-of-the-art clustering performance on a wide range of short text clustering benchmarks outperforming other strong baseline methods.

Pengfei Gao, Jingpeng Zhao, Yinglong Ma et al.

Many important classification problems in the real-world consist of a large number of closely related categories in a hierarchical structure or taxonomy. Hierarchical multi-label text classification (HMTC) with higher accuracy over large sets of closely related categories organized in a hierarchy or taxonomy has become a challenging problem. In this paper, we present a hierarchical and fine-tuning approach based on the Ordered Neural LSTM neural network, abbreviated as HFT-ONLSTM, for more accurate level-by-level HMTC. First, we present a novel approach to learning the joint embeddings based on parent category labels and textual data for accurately capturing the joint features of both category labels and texts. Second, a fine tuning technique is adopted for training parameters such that the text classification results in the upper level should contribute to the classification in the lower one. At last, the comprehensive analysis is made based on extensive experiments in comparison with the state-of-the-art hierarchical and flat multi-label text classification approaches over two benchmark datasets, and the experimental results show that our HFT-ONLSTM approach outperforms these approaches, in particular reducing computational costs while achieving superior performance.

Chen Xiaona, Ahmad Tanvir, Ma Yinglong

With the rapid development of ICT Custom Services (ICT CS) in power industries, the deployed power ICT CS systems mainly rely on the experience of customer service staff for fault type recognition, questioning, and answering, which makes it difficult and inefficient to precisely resolve the problems issued by users. To resolve this problem, in this paper, firstly, a multi-label fault text classification ensemble approach called BR-GBDT is proposed by combining Binary Relevance and Gradient Boosting Decision Tree for assisted fault type diagnosis and improving the accuracy of fault type recognition. Second, for the problem that there is lack of the training set for power ICT multi-label text classification, an automatic approach is presented to construct the training set from the historical fault text data stored in power ICT CS systems. The extensive experiments were made based on the power ICT CS training set and some general-purpose benchmark training datasets. The experiment results show that our approach outperforms the well known ensemble learning based approaches BR+LR and ML-KNN for fault text classification, efficiently handling the multi-label classification of ICT custom service text data for fault type recognition.

Gao Pengfei, Lai Dedi, Zhao Lijiao et al.

As a very popular multi-label classification method, Classifiers Chain has recently been widely applied to many multi-label classification tasks. However, existing Classifier Chains methods are difficult to model and exploit the underlying dependency in the label space, and often suffer from the problems of poorly ordered chain and error propagation. In this paper, we present a three-phase augmented Classifier Chains approach based on co-occurrence analysis for multi-label classification. First, we propose a co-occurrence matrix method to model the underlying correlations between a label and its precedents and further determine the head labels of a chain. Second, we propose two augmented strategies of optimizing the order of labels of a chain to approximate the underlying label correlations in label space, including Greedy Order Classifier Chain and Trigram Order Classifier Chain. Extensive experiments were made over six benchmark datasets, and the experimental results show that the proposed augmented CC approaches can significantly improve the performance of multi-label classification in comparison with CC and its popular variants of Classifier Chains, in particular maintaining lower computational costs while achieving superior performance.

Gao Pengfei, Ma Yinglong

Dialog Act (DA) reveals the general intent of the speaker utterance in a conversation. Accurately predicting DAs can greatly facilitate the development of dialog agents. Although researchers have done extensive research on dialog act classification, the feature information of classification has not been fully considered. This paper suggests that word cues, part-of-speech cues and statistical cues can complement each other to improve the basis for recognition. In addition, the different types of the three lead to the diversity of their distribution forms, which hinders the mining of feature information. To solve this problem, we propose a novel model based on universality and individuality strategies, called Universality-Individuality Integration Model (UIIM). UIIM not only deepens the connection between the clues by learning universality, but also utilizes the learning of individuality to capture the characteristics of the clues themselves. Experiments were made over two most popular benchmark data sets SwDA and MRDA for dialogue act classification, and the results show that extracting the universalities and individualities between cues can more fully excavate the hidden information in the utterance, and improve the accuracy of automatic dialogue act recognition.

Jingpeng Zhao, Yinglong Ma

Text classification has become increasingly challenging due to the continuous refinement of classification label granularity and the expansion of classification label scale. To address that, some research has been applied onto strategies that exploit the hierarchical structure in problems with a large number of categories. At present, hierarchical text classification (HTC) has received extensive attention and has broad application prospects. Making full use of the relationship between parent category and child category in text classification task can greatly improve the performance of classification. In this paper, We propose a joint embedding of text and parent category based on hierarchical fine-tuning ordered neurons LSTM (HFT-ONLSTM) for HTC. Our method makes full use of the connection between the upper-level and lower-level labels. Experiments show that our model outperforms the state-of-the-art hierarchical model at a lower computation cost.

Xueyan Liu, Zhitao Guan, Xiaojiang Du et al.

Nowadays, a large amount of user privacy-sensitive data is outsourced to the cloud server in ciphertext, which is provided by the data owners and can be accessed by authorized data users. When accessing data, the user should be assigned with the access permission according to his identities or attributes. In addition, the search capabilities in encrypted outsourced data is expected to be enhanced, i.e., the search results can better pre-sent user's intentions. To address the above issues, ESAS, an Efficient Semantic and Authorized Search scheme over encrypt-ed outsourced data, is proposed. In ESAS, by integrating PRSCG (the privacy-preserving ranked search based on con-ceptual graph) and CP-ABE (ciphertext policy attribute-based encryption), semantic search with file-level fine-grained access authorization can be realized. In addition, search authorization can be done in an offline manner, which can improve search efficiency and reduce the response time. The security analysis indicate that the proposed ESAS meets security requirement.

Yinglong Ma, Peng Zhang, Jiangang Ma

A previous similar case in common law systems can be used as a reference with respect to the current case such that identical situations can be treated similarly in every case. However, current approaches for judgment document similarity computation failed to capture the core semantics of judgment documents and therefore suffer from lower accuracy and higher computation complexity. In this paper, a knowledge block summarization based machine learning approach is proposed to compute the semantic similarity of Chinese judgment documents. By utilizing domain ontologies for judgment documents, the core semantics of Chinese judgment documents is summarized based on knowledge blocks. Then the WMD algorithm is used to calculate the similarity between knowledge blocks. At last, the related experiments were made to illustrate that our approach is very effective and efficient in achieving higher accuracy and faster computation speed in comparison with the traditional approaches.

Zhitao Guan, Guanlin Si, Xiaosong Zhang et al.

Intelligence is one of the most important aspects in the development of our future communities. Ranging from smart home, smart building, to smart city, all these smart infrastructures must be supported by intelligent power supply. Smart grid is proposed to solve all challenges of future electricity supply. In smart grid, in order to realize optimal scheduling, a Smart Meter (SM) is installed at each home to collect the near real-time electricity consumption data, which can be used by the utilities to offer better smart home services. However, the near real-time data may disclose user's privacy. An adversary may track the application usage patterns by analyzing the user's electricity consumption profile. In this paper, we propose a privacy-preserving and efficient data aggregation scheme. We divide users into different groups and each group has a private blockchain to record its members' data. To preserve the inner privacy within a group, we use pseudonym to hide user's identity, and each user may create multiple pseudonyms and associate his/her data with different pseudonyms. In addition, the bloom filter is adopted for fast authentication. The analysis shows that the proposed scheme can meet the security requirements, and achieve a better performance than other popular methods.

Yinglong Ma, Moyi Shi

Semantic search technology has received more attention in the last years. Compared with the keyword based search, semantic search is used to excavate the latent semantics information and help users find the information items that they want indeed. In this paper, we present a novel approach for semantic search which combines Multi-Categorization Semantic Analysis with personalization technology. The MCSA approach can classify documents into multiple categories, which is distinct from the existing approaches of classifying documents into a single category. Then, the search history and personal information for users are significantly considered in analysing and matching the original search result by Term Vector DataBase. A series of personalization algorithms are proposed to match personal information and search history. At last, the related experiments are made to validate the effectiveness and efficiency of our method. The experimental results show that our method based on MCSA and personalization outperforms some existing methods with the higher search accuracy and the lower extra time cost.