Integrating external knowledge with traditional spoken language understanding (SLU) models can effectively mitigate the ambiguity in user utterances in real-world scenarios. Knowledge graph, as a common source of external knowledge, encapsulates entities enriched with diverse attribute information. Nevertheless, existing models consider all entities as relevant, which introduces significant noise into the input. Additionally, not all attribute information of the entities is essential, resulting in considerable noise and redundancy. In this article, we propose a Noise-Removal of Knowledge-Enhanced (NRKE) framework for SLU, which involves two different types of denoising. The first approach involves hard denoising via entity selection, where we leverage a small clean dataset and introduce a BERT-based auxiliary model to filter out entities unrelated to user utterances, effectively eliminating noisy entities. In addition, we further refine entity selection by incorporating Large Language Models (LLMs) to assist in filtering out entities unrelated to user utterances. The second method involves soft denoising through the selection of entity attribute information. This approach utilizes a keywords-based local semantic selection that gives greater weight to relevant local semantics associated with specific keywords. This allows us to capture task-related information from the chosen entities, thereby minimizing noise and redundancy. To evaluate the generalization capability of existing knowledge-enhanced SLU models, we construct a new dataset named KGCAIS. The experimental results show that our NRKE achieves better performance than the competing models on both the PROSLU and KGCAIS datasets.

Large Language Models (LLMs) have demonstrated impressive capabilities in language generation and general task performance.However, their application to spoken language understanding (SLU) remains challenging-particularly for token-level tasks, where the autoregressive nature of LLMs often leads to misalignment issues.They also struggle to capture nuanced interrelations in semanticlevel tasks through direct fine-tuning alone.To address these challenges, we propose the Entitylevel Language Model (ECLM) framework, which reformulates slot-filling as an entity recognition task and introduces a novel concept, Chain of Intent, to enable step-by-step multiintent recognition.Experimental results show that ECLM significantly outperforms strong baselines such as Uni-MIS, achieving gains of 3.7% on MixATIS and 3.1% on MixSNIPS.Compared to standard supervised fine-tuning of LLMs, ECLM further achieves improvements of 8.5% and 21.2% on these datasets, respectively.Our code is available at https: //github.com/SJY8460/ECLM.

Decoder-only Large Language Models (LLMs) have demonstrated exceptional performance in language generation, exhibiting broad capabilities across various tasks. However, the application to label-sensitive language understanding tasks remains challenging due to the limitations of their autoregressive architecture, which restricts the sharing of token information within a sentence. In this paper, we address the Multi-Intent Detection (MID) task and introduce MIDLM, a bidirectional LLM framework that incorporates intent number detection and multi-intent selection. This framework allows autoregressive LLMs to leverage bidirectional information awareness through post-training, eliminating the need for training the models from scratch. Comprehensive evaluations across 8 datasets show that MIDLM consistently outperforms both existing vanilla models and pretrained baselines, demonstrating its superior performance in the MID task.

Task-oriented dialogue summarization aims to automatically extract key information to generate domain summaries to improve service efficiency and quality. Task-oriented dialogue is inherently logical and surrounds specific topic. How to effectively capture the dialogue topic and the most salient information becomes one of the major challenges of this task. In this paper, we propose a task-oriented dialogue summarization model utilizing a multi-level encoder with global topic (MLEGT). This model discovers temporal and spatial dependencies through a multi-level encoder, while simultaneously obtaining a simple yet effective global topic in the process of graph construction. It not only captures the crucial details but also breaks the long-range limit and discover the intrinsic structure across the dialogue. Then, a global topic guided pointer mechanism is added into the summrizer to capture ignored but important information, which is helpful to improve the accuracy of the summary. A comprehensive study of two public datasets, including a real-world large-scale Chinese police interrogation dataset and a medical reporting service dataset proves the superiority of our method on several strong baselines.

In real-world scenarios, due to data scarcity, cross-domain slot filling in spoken language understanding remains a significant challenge. Previous works focus on supplementing sequence labeling models with slot meta-information or metric learning. They have poor generalization capabilities lacking specific domain knowledge. To enhance generalization, recent studies introduce implicit general knowledge to enhance the performance of slots lacking domain-specific knowledge by further pretraining or larger-parameter generative models. However, this knowledge is domain-agnostic and difficult to provide comprehensive knowledge for target domain. Therefore, we propose a two-stage data generation strategy, utilizing powerful LLMs to synthesize samples to introduce knowledge for each slot of the data-scarce target domain. More importantly, we employ a data curation mechanism based on confidence and uncertainty to identify and filter out low-quality samples to obtain a high-quality synthetic dataset. Extensive experimental results demonstrate the effectiveness and generality of our approach.

So far, multi-intent spoken language understanding (SLU) has become a research hotspot in the field of natural language processing (NLP) due to its ability to recognize and extract multiple intents expressed and annotate corresponding sequence slot tags within a single utterance. Previous research has primarily concentrated on the token-level intent-slot interaction to model joint intent detection and slot filling, which resulted in a failure to fully utilize anisotropic intent-guiding information during joint training. In this work, we present a novel architecture by modeling the multi-intent SLU as a multi-view intent-slot interaction. The architecture resolves the kernel bottleneck of unified multi-intent SLU by effectively modeling the intent-slot relations with utterance, chunk, and token-level interaction. We further develop a neural framework, namely Uni-MIS, in which the unified multi-intent SLU is modeled as a three-view intent-slot interaction fusion to better capture the interaction information after special encoding. A chunk-level intent detection decoder is used to sufficiently capture the multi-intent, and an adaptive intent-slot graph network is used to capture the fine-grained intent information to guide final slot filling. We perform extensive experiments on two widely used benchmark datasets for multi-intent SLU, where our model bets on all the current strong baselines, pushing the state-of-the-art performance of unified multi-intent SLU. Additionally, the ChatGPT benchmark that we have developed demonstrates that there is a considerable amount of potential research value in the field of multi-intent SLU.

Dialogue intent classification is a pivotal task in natural language understanding, crucial for effective human-computer interactions. Despite significant progress in structural modeling of dialogues and texts, existing research still has several limitations: intention labels are treated as independent entities, ignoring the hierarchical relationships and dependencies among them and making it hard to make accurate predictions on fine-grained labels. In this paper, we propose a Hierarchical Label-aware Dialogue Intent Classification model (HLDIC) for dialogue intent classification. Specifically, we leverage the hierarchical relationships of labels by introducing a coarse-grained label classification auxiliary task. A hierarchical adaptive attention mechanism is proposed, which employs gate mechanisms to guide the model in recognizing keywords and vital adjacent pairs. To further explore label dependencies, a hierarchy-aware mechanism is proposed to use a mask matrix to allow the model to focus on the correct fine-grained labels within the corresponding coarse-grained labels and partially suppress the noise from other coarse-grained labels. Experimental results on public CCL2018-Task1 corpus show the superior performance of HLDIC.

Out-of-domain (OOD) detection plays an important role in spoken language understanding (SLU). It can help dialog systems reduce confusion between in-domain (ID) and OOD utterances. Many dialog systems train their model to achieve this goal by collecting annotated OOD and ID data. However, acquiring large-scale OOD datasets can be costly. Recent generative adversarial networks (GANs) based OOD detection methods aim to mitigate this problem. However, their performance in low-resource scenarios remains limited due to a lack of diversity in generated samples and the information contained in the distribution of real samples doesn’t get fully exploited. To address these issues, we propose an Anchor-guided GAN with Contrastive Loss (AGCL) for low-resource OOD detection. In this model, two distinct anchor distributions are established as ground-truth distributions to guide GAN training, which prevents the model from collapsing to a narrow criterion. Furthermore, we introduce an extra contrastive loss for the generator to increase the distinction between the features of generated OOD samples and the limited real OOD samples provided by the dataset, thereby enhancing their diversity. This modification subsequently results in better performance of the anchor-guided GAN. Experimental results demonstrate that our proposed method outperforms existing methods in low-resource scenarios.

Cross-domain slot filling is a widely explored problem in spoken language understanding (SLU), which requires the model to transfer between different domains under data sparsity conditions. Dominant two-step hierarchical models first extract slot entities and then calculate the similarity score between slot description-based prototypes and the last hidden layer of the slot entity, selecting the closest prototype as the predicted slot type. However, these models only use slot descriptions as prototypes, which lacks robustness. Moreover, these approaches have less regard for the inherent knowledge in the slot entity embedding to suffer from the issue of overfitting. In this letter, we propose a Robust Multi-prototypes Aware Integration (RMAI) method for zero-shot cross-domain slot filling. In RMAI, more robust slot entity-based prototypes and inherent knowledge in the slot entity embedding are utilized to improve the classification performance and alleviate the risk of overfitting. Furthermore, a multi-prototypes aware integration approach is proposed to effectively integrate both our proposed slot entity-based prototypes and the slot description-based prototypes. Experimental results on the SNIPS dataset demonstrate the well performance of RMAI.

Multi-intent spoken language understanding (SLU) that can handle multiple intents in an utterance has attracted increasing attention. Previous studies treat the slot filling task as a token-level sequence labeling task, which results in a lack of entity-related information. In our paper, we propose anEntity-LevelSlotFilling (ELSF) framework for joint multiple intent detection and slot filling. In our framework, two entity-oriented auxiliary tasks, entity boundary detection and entity type assignment, are introduced as the regularization to capture the entity boundary and the context of type, respectively. Besides, to better utilize the entity interaction, we design an effective entity-level coordination mechanism for modeling the interaction in both entity-entity and intent-entity relationships. Experiments on five datasets demonstrate the effectiveness and generalizability of our ELSF.

Massive multiplayer online role-playing games (MMORPG) have been becoming one of the most popular and exciting online games. In recent years, a cheating phenomenon called real money trading (RMT) has arisen and damaged the fantasy world in many ways. RMT is the sale of in-game items, currency, or even characters to earn real money, breaking the balance of the game economy ecosystem and damaging the game experience. Therefore, some studies have emerged to address the problem of RMT detection. However, they cannot well handle the label uncertainty problem in practice, where there are only labeled RMT samples (positive samples) and unlabeled samples, which could either be RMT samples or normal transactions (negative samples). Meanwhile, the trading relationship between RMTers is modeled in a simple way, leading to some normal transactions being falsely classified as RMT. In this article, we propose PU-Detector, a novel framework based on PU learning (learning from positive and unlabeled data) for RMT detection, considering the fact that there are only labeled RMT samples and other unlabeled transactions. We first automatically estimate the likelihood of one transaction being RMT by developing an improved PU learning method and proposing an assessment rule. Sequentially, we use the estimated likelihood as edge weight to construct a trading graph to learn trader representation. Then, with the trader representations and basic trading features, we detect RMT samples by the improved PU learning method. PU-Detector is evaluated on a large-scale real world dataset consisting of 33,809,956 transaction logs generated by 43,217 unique players. Compared with other approaches, it achieves the state-of-the-art performance and demonstrates its advantages in detecting underlying RMT samples.

Imbalanced data biases the classifier towards the majority class. Accompanied with high-dimensional characteristics, classification performance is further degraded. Existing researches for skewed data mainly involve resampling, cost-sensitive learning, and classifier ensemble. However, these approaches have some limitations: 1) resampling suffers from noisy and redundant features in high-dimensional skewed data; 2) cost-sensitive learning is hard to construct an optimal cost matrix for sample misclassification; 3) ensemble with random feature subspace easily leads to information loss; 4) ensemble with sample subspace on small-size data easily leads to insufficient description of sample space and suffers from negative impacts of high-dimensional data. This paper proposes an improved contraction-expansion subspace ensemble (ICESE) for high-dimensional imbalanced data classification. First, a contraction-expansion subspace optimization (CESO) is designed to perform subspace selection and transformation, which is beneficial for enhancing the discrimination and diversity of subspace. Then, to strengthen classification capabilities, a CESO-based multilayer optimization structure is developed to construct the improved subspace. Finally, to mitigate the effects of skewed data, ICESE performs a resampling scheme on the improved subspace for constructing a rebalanced subset to base classifier. Experimental results on 24 high-dimensional imbalanced data sets demonstrate that our ICESE outperforms different mainstream ensemble systems in terms of F-score and G-mean.

High-dimensional class imbalanced data have plagued the performance of classification algorithms seriously. Because of a large number of redundant/invalid features and the class imbalanced issue, it is difficult to construct an optimal classifier for high-dimensional imbalanced data. Classifier ensemble has attracted intensive attention since it can achieve better performance than an individual classifier. In this work, we propose a multiview optimization (MVO) to learn more effective and robust features from high-dimensional imbalanced data, based on which an accurate and robust ensemble system is designed. Specifically, an optimized subview generation (OSG) in MVO is first proposed to generate multiple optimized subviews from different scenarios, which can strengthen the classification ability of features and increase the diversity of ensemble members simultaneously. Second, a new evaluation criterion that considers the distribution of data in each optimized subview is developed based on which a selective ensemble of optimized subviews (SEOS) is designed to perform the subview selective ensemble. Finally, an oversampling approach is executed on the optimized view to obtain a new class rebalanced subset for the classifier. Experimental results on 25 high-dimensional class imbalanced datasets indicate that the proposed method outperforms other mainstream classifier ensemble methods.

Emotion Recognition in Conversation (ERC) has considerable prospects due to its wide range of applications. Most existing works integrate speaker information statically and capture a relatively consistent atmosphere in conversation. However, these works poorly track the emotional state dynamics of each party in a conversation and focus on emotion consistency. The speakers’ emotional states are independent but influence each other during the conversation. To address the above issues, we propose a Speaker Dynamics Tracking Network (SDTN) for ERC. Specifically, SDTN can dynamically track the local and global speaker states during emotional flow in conversation and capture implicit stimulation of emotional shift. Extensive experiments on MELD and EmoryNLP datasets demonstrate the superiority and effectiveness of our proposed SDTN model, and confirm that every designed module consistently benefits the performance.

High-dimensional small-size data seriously affects the performance of classifiers. By combining classifiers, ensemble learning obtains higher accuracy and more robust predictions. However, these classifier ensemble methods suffer from several limitations: 1) ensemble with sample space suffers from noise and redundant features; 2) constructing sample subspace on small-size data leads to an insufficient description of sample space; 3) ensemble with feature space leads to information loss, which will degrade performance of classifiers. To overcome the above limitations, a new classifier ensemble method based on subspace enhancement (CESE) is proposed for high-dimensional data classification. First, a superior subspace enhancement scheme (SSE) is designed to effectively implement feature selection and transformation for high-dimensional data, followed by generating multiple superior feature subspaces with diversity and discrimination, which enhances the representative ability of features. Second, we develop a mixed space enhancement process (MSE) based on multiscale rotation reconstruction and various subspace enhanced features of SSE. Furthermore, to improve the capacity of our method, we design various feature combination strategies for enhanced features from both SSE and MSE. Comparative results on 33 high-dimensional data sets indicate that our approach CESE outperforms different mainstream integrated system

It is hard to construct an optimal classifier for high-dimensional imbalanced data, on which the performance of classifiers is seriously affected and becomes poor. Although many approaches, such as resampling, cost-sensitive, and ensemble learning methods, have been proposed to deal with the skewed data, they are constrained by high-dimensional data with noise and redundancy. In this study, we propose an adaptive subspace optimization ensemble method (ASOEM) for high-dimensional imbalanced data classification to overcome the above limitations. To construct accurate and diverse base classifiers, a novel adaptive subspace optimization (ASO) method based on adaptive subspace generation (ASG) process and rotated subspace optimization (RSO) process is designed to generate multiple robust and discriminative subspaces. Then a resampling scheme is applied on the optimized subspace to build a class-balanced data for each base classifier. To verify the effectiveness, our ASOEM is implemented based on different resampling strategies on 24 real-world high-dimensional imbalanced datasets. Experimental results demonstrate that our proposed methods outperform other mainstream imbalance learning approaches and classifier ensemble methods.

Text classification has been widely explored in natural language processing. In this article, we propose a novel adaptive dense ensemble model (AdaDEM) for text classification, which includes local ensemble stage (LES) and global dense ensemble stage (GDES). To strengthen the classification ability and robustness of the enhanced layer, we propose a selective ensemble model based on enhanced attention convolutional neural networks (EnCNNs). To increase the diversity of the ensemble system, these EnCNNs are generated by using two manners: 1) different sample subsets and 2) different granularity kernels. Then, an evaluation criterion that considers both accuracy and diversity is proposed in LES to obtain effective integration results. Furthermore, to make better use of information flow, we develop an adaptive dense ensemble structure with multiple enhanced layers in GDES to mitigate the issue that there may be redundant or invalid enhanced layers in the cascade structure. We conducted extensive experiments against state-of-the-art methods on multiple real-world datasets, including long and short texts, which has verified the effectiveness and generality of our method.

Learning and classification of imbalanced data is a quite common challenge in machine learning. In order to generate more high-quality minority samples in imbalanced data and help solve the classification process, this paper proposes a novel local tangent generative adversarial network (LT-GAN). In LT-GAN, a local tangent based generator is designed to generate realistic and diverse minority class samples by learning the local tangent space of original minority samples. Meanwhile, a two-function discriminator is explored to judge the authenticity of samples and distinguish the majority samples from the minority samples. With the synthesis of minority class samples, the generator and discriminator are trained together by using adversarial learning. Experiments and comparisons show that our proposed LT-GAN outperforms other techniques and significantly improves the classification performance of imbalanced data.

Classifying high-dimensional small-size data is challenging in the field of pattern recognition. Traditional ensemble learning methods have several limitations: 1) sample-space based methods are easily affected by noise and redundant features; 2) feature-space based methods cannot excavate the essential characteristics of features; 3) feature subspaces cause information loss, which leads to a decline in accuracy; 4) most selective ensemble methods only consider the diversity and performance of sub-classifiers and ignore the impact on integration systems. To address the above limitations, we propose an adaptive classifier ensemble learning method (AdaSPEL) based on spatial perception for high-dimensional data. First, we design a local-space perception method for feature transformation, which encourages both high performance and diversity of the ensemble members. Second, we design a cross-space perception method based on the distribution of samples to obtain the cross-space enhanced features to provide a macro analysis for the characteristics of data. Furthermore, an adaptive selective ensemble method based on local and global evaluation mechanisms is proposed, which considers the impact of sub-classifiers on integrated systems. Experimental results on 33 high-dimensional data sets verify that our method outperforms mainstream ensemble learning methods based on feature space and sample space, and neural network-based algorithms.

The rapid development of modern communication technologies-in particular, (mobile) phone communications-has largely facilitated human social interactions and information exchange. However, the emergence of telemarketing frauds can significantly dissipate individual fortune and social wealth, resulting in a potential slow down or damage to economics. In this work, we propose to spot telemarketing frauds, with an emphasis on unveiling the “precise fraud” phenomenon and the strategies that are used by fraudsters to precisely select targets. To study this problem, we employ a one-month complete dataset of telecommunication metadata in Shanghai with 54 million users and 698 million call logs. Through our study, we find that user's information might have been seriously leaked, and fraudsters have a preference over the target user's age and activity in mobile network. We further propose a novel semi-supervised learning framework to distinguish fraudsters from non-fraudsters. Experimental results on a real-world data show that our approach outperforms several state-of-the-art algorithms in accuracy of detecting fraudsters (e.g., +0.278 in terms of F1 on average). We believe that our study can potentially inform policymaking for government and mobile service providers.

Online gaming is one of the most successful applications having a large number of players interacting in an online persistent virtual world through the Internet. However, some cheating players gain improper advantages over normal players by using illegal automated plugins which has brought huge harm to game health and player enjoyment. Game industries have been devoting much efforts on cheating detection with multiview data sources and achieved great accuracy improvements by applying artificial intelligence (AI) techniques. However, generating explanations for cheating detection from multiple views still remains a challenging task. To respond to the different purposes of explainability in AI models from different audience profiles, we propose the EMGCD, the first explainable multi-view game cheating detection framework driven by explainable AI (XAI). It combines cheating explainers to cheating classifiers from different views to generate individual, local and global explanations which contributes to the evidence generation, reason generation, model debugging and model compression. The EMGCD has been implemented and deployed in multiple game productions in NetEase Games, achieving remarkable and trustworthy performance. Our framework can also easily generalize to other types of related tasks in online games, such as explainable recommender systems, explainable churn prediction, etc.

Microcredit, very small loans given out without any collaterals, is a new form of financial instrument that serves the segment of population that are typically underserved by traditional financial services. When microcredit takes the form of lending over the internet, it has the advantage of easy online application process and fast funding for borrowers, as well as attractive rate of return for individual lenders. For platforms that facilitate such activities, the key challenge lies in risk management, i.e. adequately pricing each loan's risk so as to balance borrowers' lending cost and lenders' risk-adjusted return. In fact, identifying default borrowers is of critical importance for the ecosystem. Traditionally, credit risk depends heavily on borrowers' historical loan records. However, most borrowers do not have any bureau history, and therefore cannot provide sufficient loan records. In this paper, we study default prediction in online lending by using social behavior. Specifically, we based our work on a dataset provided by PPDai, one of the leading platforms in China. Our dataset consists of over 11 million users and more than 1.5 billion call logs between them. We establish a mobile network and explore social factors that predict borrowers' default. Based on this, we focused on cheating agents, who recruit and teach borrowers to cheat by providing false information and faking application materials. Cheating agents represent a type of default, especially detrimental to the system. We propose a novel probabilistic framework to identify default borrowers and cheating agents simultaneously. Experimental results on production dataset demonstrate significant improvement over several baseline methods. Moreover, our model can effectively identify cheating agents without any labels.

This paper presents a new patch-based video restoration scheme. By grouping similar patches in the spatiotemporal domain, we formulate the video restoration problem as a joint sparse and low-rank matrix approximation problem. The resulting nuclear norm and $\ell_1$ norm related minimization problem can also be efficiently solved by many recently developed numerical methods. The effectiveness of the proposed video restoration scheme is illustrated on two applications: video denoising in the presence of random-valued noise, and video in-painting for archived films. The numerical experiments indicate that the proposed video restoration method compares favorably against many existing algorithms.

Most existing video denoising algorithms assume a single statistical model of image noise, e.g. additive Gaussian white noise, which often is violated in practice. In this paper, we present a new patch-based video denoising algorithm capable of removing serious mixed noise from the video data. By grouping similar patches in both spatial and temporal domain, we formulate the problem of removing mixed noise as a low-rank matrix completion problem, which leads to a denoising scheme without strong assumptions on the statistical properties of noise. The resulting nuclear norm related minimization problem can be efficiently solved by many recently developed methods. The robustness and effectiveness of our proposed denoising algorithm on removing mixed noise, e.g. heavy Gaussian noise mixed with impulsive noise, is validated in the experiments and our proposed approach compares favorably against some existing video denoising algorithms.