Conditional Knowledge Graphs (CKGs) extend traditional knowledge graphs by incorporating conditional constraints, enabling a more accurate understanding of complex knowledge with conditional constraints for the semantic web. Conditional information extraction (CIE) aims to extract not only traditional fact triples but also their corresponding conditional qualifiers, forming quintuples that represents these constraints. Existing CIE methods typically treat conditional quintuples as flat structures, overlooking the hierarchical dependencies. Additionally, they often require exploring all possible mention combinations, leading to a large interaction space. These two issues hinder the extraction performance. To this end, we propose a Diffusion Model on Fact-condition Star Graph for CIE (Diff-CIE). We adapt a star graph structure where fact triples serve as central nodes and conditional tuples as leaf nodes, explicitly modeling the hierarchical dependencies. We then leverage the diffusion model to reformulate CIE as a progressive denoising process on these nodes, refining a fixed number of noised nodes into quintuples, thereby reducing the interaction space. Furthermore, to mitigate the inherent optimization instability in traditional diffusion-based information extraction methods, we introduce a deterministic in-order matching strategy to provide an auxiliary constraint. Extensive experiments on three datasets demonstrate that Diff-CIE consistently outperforms state-of-the-art baselines and has higher efficiency, achieving an improvement in F1 metric of over 1.19%, validating the effectiveness of our methods.

In computational advertising, platforms are increasingly optimizing toward advertisers' real assessment metrics to help achieve more reliable advertising performance. Consequently, predicting customers' Lifetime Value (LTV) has become an essential component of the advertising system, as it directly impacts the actual Return On Investment (ROI) of advertisers. Recent research on LTV prediction primarily focuses on the ranking stage, lacking consideration of the initial retrieval stage. This oversight may lead to the inconsistency between retrieval and ranking, resulting in a loss of efficiency. Unlike the LTV estimation in the ranking stage, the retrieval stage faces more severe data sparsity and constraints inherent in online scoring. Incorporating rich data from other domains can mitigate the sparsity while introducing the negative transfer issue. To tackle these challenges, we introduce Retrieval-LTV, a two-tower retrieval model for LTV prediction. This model employs a cooperative framework and incorporates a fine-grained evaluation for each sample across each expert, thereby enhancing effective selective learning from the source domain while mitigating the risk of negative transfer. Additionally, we have designed a specialized representation transformation to obtain the LTV-oriented score for online retrieval. Experiments on three real-world industrial datasets demonstrate that Retrieval-LTV outperforms all the baselines, achieving superior performance. An online A/B test further confirms the effectiveness of Retrieval-LTV, increasing the overall LTV by 2.08%. As a result, Retrieval-LTV has now been fully deployed in Tencent Ads.

Domain generalization (DG) tasks aim to learn cross-domain models from source domains and apply them to unknown target domains. Recent research has demonstrated that diverse and rich source domain samples can enhance domain generalization capability. This work argues that the impact of each sample on the model's generalization ability varies. Even a small-scale but high-quality dataset can achieve a notable level of generalization. Motivated by this, we propose a domain-adversarial active learning (DAAL) algorithm for classification tasks in DG. First, we analyze that the objective of DG tasks is to maximize the inter-class distance within the same domain and minimize the intra-class distance across different domains. We design a domain adversarial selection method that prioritizes challenging samples in an active learning (AL) framework. Second, we hypothesize that even in a converged model, some feature subsets lack discriminatory power within each domain. We develop a method to identify and optimize these feature subsets, thereby maximizing inter-class distance of features. Lastly, We experimentally compare our DAAL algorithm with various DG and AL algorithms across four datasets. The results demonstrate that the DAAL algorithm can achieve strong generalization ability with fewer data resources, thereby significantly reducing data annotation costs in DG tasks.

The widespread adoption of location-based applications has created a growing demand for point-of-interest (POI) recommendation, which aims to predict a user’s next POI based on their historical check-in data and current location. However, existing methods often struggle to capture the intricate relationships within check-in data. This is largely due to their limitations in representing temporal and spatial information and underutilizing rich semantic features. While large language models (LLMs) offer powerful semantic comprehension to solve them, they are limited by hallucination and the inability to incorporate global collaborative information. To address these issues, we propose a novel method SeCor, which treats POI recommendation as a multi-modal task and integrates semantic and collaborative representations to form an efficient hybrid encoding. SeCor first employs a basic collaborative filtering model to mine interaction features. These embeddings, as one modal information, are fed into LLM to align with semantic representation, leading to efficient hybrid embeddings. To mitigate the hallucination, SeCor recommends based on the hybrid embeddings rather than directly using the LLM’s output text. Extensive experiments on three public real-world datasets show that SeCor outperforms all baselines, achieving improved recommendation performance by effectively integrating collaborative and semantic information through LLMs.

Event extraction is an essential but challenging task in information extraction. This task has considerably benefited from pre-trained language models, such as BERT. However, when it comes to the trigger-word mismatch problem in languages without natural delimiters, existing methods ignore the complement of lexical information to BERT. In addition, the inherent multi-role noise problem could limit the performance of methods when one sentence contains multiple events. In this article, we propose a Mask-Attention-based BERT (MABERT) framework for Chinese event extraction to address the above problems. Firstly, in order to avoid trigger-word mismatch and integrate lexical features into BERT layers directly, a mask-attention-based transformer augmented with two mask matrices is devised to replace the original one in BERT. By the mask-attention-based transformer, the character sequence interacts with external lexical semantics sufficiently and keeps its structure information at the same time. Moreover, against the multi-role noise problem, we make use of event type information from representation and classification, two aspects to enrich entity features, where type markers and event-schema-based mask matrix are proposed. Experimental results on the widely used ACE2005 dataset show the effectiveness of our proposed MABERT on Chinese event extraction task compared with other state-of-the-art methods.

The Knowledge graph (KG) uses the triples to describe the facts in the real world. It has been widely used in intelligent analysis and applications. However, possible noises and conflicts are inevitably introduced in the process of constructing. And the KG based tasks or applications assume that the knowledge in the KG is completely correct and inevitably bring about potential deviations. In this paper, we establish a knowledge graph triple trustworthiness measurement model that quantify their semantic correctness and the true degree of the facts expressed. The model is a crisscrossing neural network structure. It synthesizes the internal semantic information in the triples and the global inference information of the KG to achieve the trustworthiness measurement and fusion in the three levels of entity level, relationship level, and KG global level. We analyzed the validity of the model output confidence values, and conducted experiments in the real-world dataset FB15K (from Freebase) for the knowledge graph error detection task. The experimental results showed that compared with other models, our model achieved significant and consistent improvements.

Task-specific word identification aims to choose the task-related words that best describe a short text. Existing approaches require well-defined seed words or lexical dictionaries (e.g., WordNet), which are often unavailable for many applications such as social discrimination detection and fake re view detection. However, we often have a set of labeled short texts where each short text has a task-related class label, e.g., discriminatory or non-discriminatory, specified by users or learned by classification algorithms. In this paper, we focus on identifying task-specific words and phrases from short texts by exploiting their class labels rather than using seed words or lexical dictionaries. We consider the task-specific word and phrase identification as feature learning. We train a convolutional neural network over a set of labeled texts and use score vectors to localize the task-specific words and phrases. Experimental results on sentiment word identification show that our approach significantly outperforms existing methods. We further conduct two case studies to show the effectiveness of our approach. One case study on a crawled tweets dataset demonstrates that our approach can successfully capture the discrimination-related words/phrases. The other case study on fake review detection shows that our approach can identify the fake-review words/phrases.

Named entity relation extraction is an important subject in the field of information extraction. Although many English extractors have achieved reasonable performance, an effective system for Chinese relation extraction remains undeveloped due to the lack of Chinese annotation corpora and the specificity of Chinese linguistics. Here, we summarize three kinds of unique but common phenomena in Chinese linguistics. In this article, we investigate unsupervised linguistics-based Chinese open relation extraction (ORE), which can automatically discover arbitrary relations without any manually labeled datasets, and research the establishment of a large-scale corpus. By mapping the entity relations into dependency-trees and considering the unique Chinese linguistic characteristics, we propose a novel unsupervised Chinese ORE model based on Dependency Semantic Normal Forms (DSNFs). This model imposes no restrictions on the relative positions among entities and relationships and achieves a high yield by extracting relations mediated by verbs or nouns and processing the parallel clauses. Empirical results from our model demonstrate the effectiveness of this method, which obtains stable performance on four heterogeneous datasets and achieves better precision and recall in comparison with several Chinese ORE systems. Furthermore, a large-scale knowledge base of entity and relation, called COER, is established and published by applying our method to web text, which conquers the trouble of lack of Chinese corpora.

Named Entity Recognition (NER) is an important basis for the tasks in natural language processing such as relation extraction, entity linking and so on. The common method of existing Chinese NER systems is to use the character sequence as the input, and the intention is to avoid the word segmentation. However, the character sequence cannot express enough semantic information, so that the recognition accuracy of Chinese NER is not as good as western language such as English. To solve this issue, we propose a Chinese NER method based on Character-Word Mixed Embedding (CWME), and the method is in accord with the pipeline of Chinese natural language processing. Our experiments show that incorporating CWME can effectively improve the performance for the Chinese corpus with state-of-the-art neural architectures widely used in NER, and the proposed method yields nearly 9% absolute improvement over previously results.

QoS-aware Web service composition has recently become one of the most challenging research issues. Although much work has been investigated to solve the problem, they mainly focus on certain QoS of Web services, while QoS with uncertainty exposes the most important characteristic in a real and highly dynamic environment on the Internet. In this paper, with the consideration of uncertain service QoS, we model the issue of Web service composition with QoS uncertainty that is translated into a multi-objective optimization problem via uncertain interval number, which can be solved by our proposed approach via an non-deterministic multi-objective evolutionary algorithm using the strategy of decomposition. Large-scale empirical experiments have been conducted on our simulated datasets. The experimental results demonstrate that our proposed approach can effectively and efficiently find an optimum composite service solution set with satisfactory convergence.

Discrimination discovery is the data mining problem of unveiling discriminatory practices by analyzing a dataset of historical decision records. In this paper, we focus on discovering discrimination from tweets using deep learning models. One challenge here is that it is dicult to obtain a large well-labeled dataset required by the training of deep learning models for the purpose of discrimination analysis. We develop a two-phase deep learning model to address this challenge. Our model rst learns text representations based on weakly-labeled tweets (containing some specic hashtags), then trains the classier

The paper presents deep learning models for tweets binary classification. Our approach is based on the Long Short-Term Memory (LSTM) recurrent neural network and hence expects to be able to capture long-term dependencies among words. We develop two models for tweets classification. The basic model, called LSTM-TC, takes word embeddings as input, uses the LSTM layer to derive semantic tweet representation, and applies logistic regression to predict tweet label. The basic LSTM-TC model, like other deep learning models, requires a large amount of well-labeled training data to achieve good performance. To address this challenge, we further develop an improved model, called LSTM-TC*, that incorporates a large amount of weakly-labeled data for classifying tweets. We present two approaches of constructing the weakly-labeled data. One is based on hashtag information and the other is based on the prediction output of some traditional classifier that does not need a large amount of well-labeled training data. Our LSTM-TC* model first learns tweet representation based on the weakly-labeled data, and then trains the logistic regression classifier based on the small amount of well-labeled data. Experimental results show that: (1) the proposed method can be successfully used for tweets classification and outperform existing state-of-the-art methods, (2) pre-training tweet representation, which utilizes weakly-labeled tweets, can significantly improve the accuracy of tweets classification.

MapReduce has become a major computing model for data intensive applications. Hadoop, an open source implementation of MapReduce, has been adopted by an increasingly growing user community. Cloud computing service providers such as Amazon EC2 Cloud offer the opportunities for Hadoop users to lease a certain amount of resources and pay for their use. However, a key challenge is that cloud service providers do not have a resource provisioning mechanism to satisfy user jobs with deadline requirements. Currently, it is solely the user's responsibility to estimate the required amount of resources for running a job in the cloud. This paper presents a Hadoop job performance model that accurately estimates job completion time and further provisions the required amount of resources for a job to be completed within a deadline. The proposed model builds on historical job execution records and employs Locally Weighted Linear Regression (LWLR) technique to estimate the execution time of a job. Furthermore, it employs Lagrange Multipliers technique for resource provisioning to satisfy jobs with deadline requirements. The proposed model is initially evaluated on an in-house Hadoop cluster and subsequently evaluated in the Amazon EC2 Cloud. Experimental results show that the accuracy of the proposed model in job execution estimation is in the range of 94.97 and 95.51 percent, and jobs are completed within the required deadlines following on the resource provisioning scheme of the proposed model.

ABSTRACT Nowadays, social network site (SNS) has been a popular platform for information sharing and dissemination. However, because of unknown information sources or unfamiliar recommenders, users of SNS may receive thousands of recommending information, which contain potential risks to receivers. To meet the challenge of confirming reliabilities of recommendations, a novel method of recommended trust computation is proposed in this paper. Firstly, according to the elements of users' relationships and community characteristics in SNS, concepts of belief and reputation are defined to express subjective trustable relationship among individuals and objective trust view. Then, recommended trust computation is presented on the basis of aforementioned two concepts. The recommended trust computation is divided into two aspects, that is, recommended trust computation with different route composition and recommendation optional confidence. Further, a SNS recommended trust computation framework is proposed. Finally, examinations are given to further explain the efficiency and feasibility of our mechanism. Copyright © 2014 John Wiley & Sons, Ltd.

Web service composition (WSC) is the task of combining a chain of connected single services together to create a more complex and value-added composite service. Quality of service (QoS) has been mostly applied to represent nonfunctional properties of web services and differentiate those with the same functionality. Many research has been done on QoS-aware service composition, as it significantly affects the quality of a composite service. However, existing methods are restricted to predefined workflows, which can incur a couple of limitations, including the lack of guarantee for the optimality on overall QoS and for the completeness of finding a composite service solution. In this paper, instead of predefining a workflow model for service composition, we propose a novel planning-based approach that can automatically convert a QoS-aware composition task to a planning problem with temporal and numerical features. Furthermore, we use state-of-the-art planners, including an existing one and a self-developed one, to handle complex temporal planning problems with logical reasoning and numerical optimization. Our approach can find a composite service graph with the optimal overall QoS value while satisfying multiple global QoS constraints. We implement a prototype system and conduct extensive experiments on large web service repositories. The experimental results show that our proposed approach largely outperforms existing ones in terms of solution quality and is efficient enough for practical deployment.

For Web service composition, choreography has recently received great attention and demonstrated a few key advantages over orchestration such as distributed control, fairness, data efficiency, and scalability. Automated design of choreography plans, especially distributed plans for multiple roles, is more complex and has not been studied before. Existing work requires manual generation assisted by model checking. In this paper, we propose a novel planning-based approach that can automatically convert a given composition task to a distributed choreography specification. Although planning has been used for orchestration, it is difficult to use planning for choreography, as it involves decentralized control, concurrent workflows, and contingency. We propose a few novel techniques, including compilation of contingencies, dependency graph analysis, and communication control, to handle these characteristics using planning. We theoretically show the correctness of this approach and empirically evaluate its practicability.

Enabling accurate analysis of social network data while preserving differential privacy has been challenging since graph features such as clustering coefficient or modularity often have high sensitivity, which is different from traditional aggregate functions (e.g., count and sum) on tabular data. In this paper, we treat a graph statistics as a function f and develop a divide and conquer approach to enforce differential privacy. The basic procedure of this approach is to first decompose the target computation f into several less complex unit computations f1, · · · , fmconnected by basic mathematical operations (e.g., addition, subtraction, multiplication, division), then perturb the output of each fiwith Laplace noise derived from its own sensitivity value and the distributed privacy threshold ϵi, and finally combine those perturbed fias the perturbed output of computation f. We examine how various operations affect the accuracy of complex computations. When unit computations have large global sensitivity values, we enforce the differential privacy by calibrating noise based on the smooth sensitivity, rather than the global sensitivity. By doing this, we achieve the strict differential privacy guarantee with smaller magnitude noise. We illustrate our approach by using clustering coefficient, which is a popular statistics used in social network analysis. Empirical evaluations show the developed divide and conquer approach outperforms the direct approach.