Data & Knowledge Engineering最新文献

{"title":"FKQG: Few-shot question generation from knowledge graph via large language model in-context learning","authors":"Ruishen Liu ,&nbsp;Shaorong Xie ,&nbsp;Xinzhi Wang ,&nbsp;Xiangfeng Luo ,&nbsp;Hang Yu","doi":"10.1016/j.datak.2025.102528","DOIUrl":"10.1016/j.datak.2025.102528","url":null,"abstract":"<div><div>Knowledge Base Question Generation (KBQG) focuses on generating natural language questions from a set of triplets and answers, playing a crucial role in applications such as personalized question-answering systems and educational evaluation tools. Currently, most previous work trains the models based on a large-scale dataset, leading to degraded performance in low-resource scenarios. To address this issue, we propose a novel framework for KBQG using in-context learning with large language models (LLMs) in few-shot settings (FKQG). The key to in-context learning lies in selecting relevant examples to construct prompts that guide the LLM. Therefore, we introduce two strategies for example selection: (1) extracting the semantic paths of triplets as seeds to organize the data, and (2) using the relation linking to the answer as an additional seed. Based on these seeds, examples are retrieved from the data and reranked through graph edit distance, optimizing the prompt structure. This approach ensures contextually relevant question generation. We evaluate FKQG through extensive experiments on two benchmark datasets. Our framework outperforms existing KBQG models in few-shot scenarios, achieving up to a 4.73% improvement in ROUGE-L. Additionally, FKQG enhances the performance of knowledge-based question-answering systems, yielding a 1.2% increase in Hit@1.</div></div>","PeriodicalId":55184,"journal":{"name":"Data & Knowledge Engineering","volume":"161 ","pages":"Article 102528"},"PeriodicalIF":2.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145416217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An interpretable knowledge recommendation method for civil dispute mediation","authors":"Ning Wang,&nbsp;Shibo Cui,&nbsp;Jing Zhang,&nbsp;Runzhe Wang,&nbsp;Yongping Yu","doi":"10.1016/j.datak.2025.102527","DOIUrl":"10.1016/j.datak.2025.102527","url":null,"abstract":"<div><div>The demand for efficient and fair civil dispute mediation is driving the development of intelligent knowledge recommendation technologies. However, existing approaches face challenges in interpretability and reasoning over complex relationships. This study proposes an Interpretable Knowledge Recommendation Method (IKRM) that integrates deep learning and multi-hop reasoning to provide precise and transparent decision support for online mediation platforms. First, to address the extraction of specialized terms and intricate relationships in legal texts, we propose a pre-trained model-based semi-joint extraction method combined with ontology design, constructing a civil dispute knowledge graph that enables hierarchical semantic modeling of legal concepts. Second, we design a hybrid multi-hop reasoning framework that combines neural logic programming for numerical rule-based latent relation mining and cognitive graphs for multi-path reasoning, dynamically generating traceable explanations during path expansion. IKRM performs better than mainstream baseline models in terms of all key evaluation indicators, according to experiments validated using multi-source Chinese legal datasets. It additionally exhibits greater reasoning robustness for difficult queries. This study creates a new paradigm for legal knowledge recommendation systems that is modular, interpretable, and effective. It also contributes to larger social equitable governance by offering accurate decision assistance for civil dispute mediation in China.</div></div>","PeriodicalId":55184,"journal":{"name":"Data & Knowledge Engineering","volume":"161 ","pages":"Article 102527"},"PeriodicalIF":2.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145319484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Temporal knowledge graph recommendation with sequence-aware and path reasoning","authors":"Yuanming Zhang,&nbsp;Ziyou He,&nbsp;Yongbiao Lou,&nbsp;Haixia Long,&nbsp;Fei Gao","doi":"10.1016/j.datak.2025.102522","DOIUrl":"10.1016/j.datak.2025.102522","url":null,"abstract":"<div><div>Knowledge graph recommendation (KGRec) models not only alleviate the issues of data sparsity and the cold start problem encountered by traditional models but also enhance interpretability and credibility through the provision of explicit recommendation rationales. Nonetheless, existing KGRec models predominantly concentrate on extracting static structural features of user preferences from KG, often neglecting the dynamic temporal features, such as purchase time and click time. This oversight results in considerable limitations in recommendation performance. In response to this challenge, this paper introduces a novel temporal knowledge graph recommendation model (TKGRec), which fully utilizes both dynamic temporal feature and static structure feature for better recommendation. We specifically construct a temporal KG that encapsulates both static and dynamic user–item interactions. Based on the new environment, we propose a sequence-aware and path reasoning framework, in which the sequence-aware module employs a dual-attention mechanism to distill temporal features from interactions, whereas the path reasoning module utilizes reinforcement learning to extract path features. These two modules are seamlessly fused and iteratively refined to capture a more holistic understanding of user preferences. Experimental results on three real-world datasets demonstrate that the proposed model significantly outperforms existing state-of-the-art baseline models in terms of performance.</div></div>","PeriodicalId":55184,"journal":{"name":"Data & Knowledge Engineering","volume":"161 ","pages":"Article 102522"},"PeriodicalIF":2.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145266450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semantic-aware query answering with Large Language Models","authors":"Paolo Atzeni ,&nbsp;Teodoro Baldazzi ,&nbsp;Luigi Bellomarini ,&nbsp;Eleonora Laurenza ,&nbsp;Emanuel Sallinger","doi":"10.1016/j.datak.2025.102494","DOIUrl":"10.1016/j.datak.2025.102494","url":null,"abstract":"<div><div>In the modern data-driven world, answering queries over heterogeneous and semantically inconsistent data remains a significant challenge. Modern datasets originate from diverse sources, such as relational databases, semi-structured repositories, and unstructured documents, leading to substantial variability in schemas, terminologies, and data formats. Traditional systems, constrained by rigid syntactic matching and strict data binding, struggle to capture critical semantic connections and schema ambiguities, failing to meet the growing demand among data scientists for advanced forms of flexibility and context-awareness in query answering. In parallel, the advent of Large Language Models (LLMs) has introduced new capabilities in natural language interpretation, making them highly promising for addressing such challenges. However, LLMs alone lack the systematic rigor and explainability required for robust query processing and decision-making in high-stakes domains. In this paper, we propose Soft Query Answering (Soft QA), a novel hybrid approach that integrates LLMs as an intermediate semantic layer within the query processing pipeline. Soft QA enhances query answering adaptability and flexibility by injecting semantic understanding through context-aware, schema-informed prompts, and leverages LLMs to semantically link entities, resolve ambiguities, and deliver accurate query results in complex settings. We demonstrate its practical effectiveness through real-world examples, highlighting its ability to resolve semantic mismatches and improve query outcomes without requiring extensive data cleaning or restructuring.</div></div>","PeriodicalId":55184,"journal":{"name":"Data & Knowledge Engineering","volume":"161 ","pages":"Article 102494"},"PeriodicalIF":2.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144830326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ABBA: Index structure for sequential pattern-based aggregate queries","authors":"Witold Andrzejewski,&nbsp;Tadeusz Morzy,&nbsp;Maciej Zakrzewicz","doi":"10.1016/j.datak.2025.102506","DOIUrl":"10.1016/j.datak.2025.102506","url":null,"abstract":"<div><div>Pattern-based aggregate (PBA) queries constitute an important and widely used type of analytical queries in sequence OLAP (S-OLAP) systems. Unfortunately, finding accurate answers to PBA queries in the S-OLAP system is often very expensive both in terms of time and memory consumption. In this paper we propose an efficient and easily maintainable index structure called the ABBA Index, which addresses the problem of PBA query processing.</div><div>Experiments conducted using the KDD Cup data and public transport passengers’ travel behavior data show that our index outperforms state-of-the art solutions while requiring much less memory. The ABBA Index can be easily extended to support pattern-based aggregate queries over hierarchy (PBA-H), a novel class of analytical queries which we introduce as the second main contribution of the paper. Sensitivity, scalability and complexity analysis of the ABBA Index is also provided.</div></div>","PeriodicalId":55184,"journal":{"name":"Data & Knowledge Engineering","volume":"161 ","pages":"Article 102506"},"PeriodicalIF":2.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144911761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A fine-grained multi-lingual opinion mining method on social media texts using multi-scale fused features-based adaptive residual convolutional LSTM with attention mechanism","authors":"D. Kavitha,&nbsp;Ashwin Kumar S,&nbsp;Divya Priya B A,&nbsp;M V Guru Prasadh,&nbsp;Sri Krishna S,&nbsp;Sidh Parakh,&nbsp;Shriram. V,&nbsp;Tabish Rashid","doi":"10.1016/j.datak.2025.102524","DOIUrl":"10.1016/j.datak.2025.102524","url":null,"abstract":"<div><div>Multilingual opinion mining has grown within Natural Language Processing (NLP), particularly in the setting of social media. Because it offers valuable data from content provided by users, social networks have grown exponentially in recent years, enabling people to express their opinions and share their ideas on a variety of subjects. Many Sentiment Analysis (SA) strategies have been developed subsequently to gather emotional information from the feedback. The primary limitations of these methods include longer training time and decreased accuracy. To solve this issue, the research work introduced a multi-lingual opinion mining model for analyzing public opinions that are useful in businesses and organizations. Firstly, the texts from social media are accumulated from standard data sources. The collected texts are pre-processed to remove unnecessary content, including promotional content and spam texts. Next, the features from pre-processed text are extracted using techniques including Bidirectional Encoder Representations from Transformers (BERT), N-gram and word2vec. Here, BERT understand the sentiment of a word based on its surrounding words, allowing for more accurate sentiment detection, particularly in complex linguistic structures present in different languages. Further, N-grams extract the features from multilingual datasets, where different languages may have unique syntactic and semantic structures. Word2Vec can effectively capture phrases and idioms that convey specific sentiments. This is particularly beneficial in multilingual contexts where expressions may vary significantly between languages. The extracted features from BERT, N-gram and word2vec are given to the developed Multi-scale Fused Features based Adaptive Residual Convolutional Long Short-Term Memory with Attention mechanism (MARCLA) for analyzing the opinion of the public in different languages. Here, the sentiments expressed in the complex and varied text data are accurately interpreted by the Residual Conv-LSTM. The multiscale mechanism captures the micro and the macro level linguistic features, and the residual connections combat the issues of vanishing gradient, which aid in effectively training the deep network. In addition, the parameters from the suggested MARCLA are optimized using a Modified Random Function-based Parrot Optimizer (MRFPO). This model is beneficial in understanding public sentiment more effectively. The suggested opinion mining model’s performance is compared with conventional techniques to ensure our model’s ability. The accuracy of the designed MRFPO- MARCLA framework is 95.12 %, which is higher than the conventional frameworks like CNN, LSTM, CoNBiLSTM and MARCLA, respectively. Thus, the experimental findings demonstrated that the developed multi-lingual opinion mining approach can effectively help the organizations to monitor sentiment changes and public reactions across different languages.</div></div>","PeriodicalId":55184,"journal":{"name":"Data & Knowledge Engineering","volume":"161 ","pages":"Article 102524"},"PeriodicalIF":2.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145319483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ASF: A novel associative scoring function for embedded knowledge graph reasoning","authors":"MVPT Lakshika,&nbsp;HA Caldera","doi":"10.1016/j.datak.2025.102511","DOIUrl":"10.1016/j.datak.2025.102511","url":null,"abstract":"<div><div>One of the most important tools for knowledge management is the Knowledge Graph (KG), a multi-relational graph that depicts rich factual information across entities. A KG represents entities as nodes and relations as edges, with each edge represented by a triplet: (head entity, relation, tail entity). The Scoring Function (SF) in a KG quantifies the plausibility of these triplets and is often derived from KG embeddings. However, due to the distinct relational patterns across KGs, an SF that performs well on one KG might fail on another, making the design of optimal SFs a challenging task. This study introduces the concept of an Associative Scoring Function (ASF), which leverages Association Rule Mining (ARM) to discover and incorporate patterns and characteristics of symmetric, asymmetric, inverse, and other relational types within embedded KGs. The ARM technique in ASF uses the FP-Growth algorithm to extract meaningful associations, which is enhanced further through hyperparameter tuning. Extensive experiments on benchmark datasets demonstrate that ASF is KG-independent and performs better than state-of-the-art SFs. These results highlight ASF's potential to generalize across diverse KGs, offering a significant advancement in the KG link prediction task.</div></div>","PeriodicalId":55184,"journal":{"name":"Data & Knowledge Engineering","volume":"161 ","pages":"Article 102511"},"PeriodicalIF":2.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145094813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Source-Free Domain Adaptation with complex distribution considerations for time series data","authors":"Jing Shang,&nbsp;Zunming Chen,&nbsp;Zhiwen Xiao,&nbsp;Zhihui Wu,&nbsp;Yifei Zhang,&nbsp;Jibing Wang","doi":"10.1016/j.datak.2025.102501","DOIUrl":"10.1016/j.datak.2025.102501","url":null,"abstract":"<div><div>Source-Free Domain Adaptation (SFDA) aims to adapt a pre-trained model from a labeled source domain to an unlabeled target domain without accessing source domain data, thereby protecting source domain privacy. Although SFDA has recently been applied to time series data, the inherent complex distribution characteristics including temporal variability and distributional diversity of such data remain underexplored. Time series data exhibit significant dynamic variability influenced by collection environments, leading to discrepancies between sequences. Additionally, multidimensional time series data face distributional diversity across dimensions. These complex characteristics increase the learning difficulty for source models and widen the adaptation gap between the source and target domains. To address these challenges, this paper proposes a novel SFDA method for time series data, named Adaptive Latent Subdomain feature extraction and joint Prediction (ALSP). The method divides the source domain, which has a complex distribution, into multiple latent subdomains with relatively simple distributions, thereby effectively capturing the features of different subdistributions. It extracts latent domain-specific and domain-invariant features to identify subdomain-specific characteristics. Furthermore, it combines domain-specific classifiers and a domain-invariant classifier to enhance model performance through multi-classifier joint prediction. During target domain adaptation, ALSP reduces domain dependence by extracting invariant features, thereby narrowing the distributional gap between the source and target domains. Simultaneously, it leverages prior knowledge from the source domain distribution to support the hypothesis space and dynamically adapt to the target domain. Experiments on three real-world datasets demonstrate that ALSP achieves superior performance in cross-domain time series classification tasks, significantly outperforming existing methods.</div></div>","PeriodicalId":55184,"journal":{"name":"Data & Knowledge Engineering","volume":"161 ","pages":"Article 102501"},"PeriodicalIF":2.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144918105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Conceptual modeling: A large language model assistant for characterizing research contributions","authors":"Stephen W. Liddle ,&nbsp;Heinrich C. Mayr ,&nbsp;Oscar Pastor ,&nbsp;Veda C. Storey ,&nbsp;Bernhard Thalheim","doi":"10.1016/j.datak.2025.102497","DOIUrl":"10.1016/j.datak.2025.102497","url":null,"abstract":"<div><div>The body of conceptual modeling research publications is vast and diverse, making it challenging for a single researcher or research group to fully comprehend the field’s overall development. Although some approaches have been proposed to help organize these research contributions, it is still unrealistic to expect human experts to manually comprehend and characterize all of this research. However, as generative AI tools based on large language models, such as ChatGPT, become increasingly sophisticated, it may be possible to replace or augment tedious, manual work with semi-automated approaches. In this research, we present a customized version of ChatGPT that is tuned to the task of characterizing conceptual modeling research. Experiments with this AI tool demonstrate that it is feasible to create a usable knowledge survey for the continually evolving body of conceptual modeling research contributions.</div></div>","PeriodicalId":55184,"journal":{"name":"Data & Knowledge Engineering","volume":"161 ","pages":"Article 102497"},"PeriodicalIF":2.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Time-Aware Complex Question Answering over Temporal Knowledge Graph","authors":"Luyi Bai,&nbsp;Tongyue Zhang,&nbsp;Guangchen Feng","doi":"10.1016/j.datak.2025.102503","DOIUrl":"10.1016/j.datak.2025.102503","url":null,"abstract":"<div><div>Knowledge Graph Question Answering (KGQA) is a crucial topic in Knowledge Graphs (KGs), with the objective of retrieving the corresponding facts from KGs to answer given questions. In practical applications, facts in KGs usually have time constraints, thus, question answering on Temporal Knowledge Graphs (TKGs) has attracted extensive attention. Existing Temporal Knowledge Graph Question Answering (TKGQA) methods focus on dealing with complex questions involving multiple facts, and mainly face two challenges. First, these methods only consider matching questions with facts in TKGs to identify the answer, ignoring the temporal order between different facts, which makes it challenging to solve the questions involving temporal order. Second, they usually focus on the representation of the question text while neglecting the rich semantic information within the questions, which leads to certain limitations in understanding question. To address the above challenges, this research proposes a model named Time-Aware Complex Question Answering (TA-CQA). Specifically, we extend the Temporal Knowledge Graph Embedding (TKGE) model by incorporating temporal order information into the embedding vectors, ensuring that the model can distinguish the temporal order of different facts. To enhance the semantic representation of the question, we integrate question information using attention mechanism and learnable encoder. Different from the previous TKGQA methods, we propose time relevance measurement to further enhance the accuracy of answer prediction by better capturing the correlation between question information and time information. Multiple sets of experiments on CronQuestions and TimeQuestions demonstrate our model’s superior performance across all question types. In particular, for complex questions involving multiple facts, the hit@1 values are increased by 3.2% and 3.5% respectively.</div></div>","PeriodicalId":55184,"journal":{"name":"Data & Knowledge Engineering","volume":"161 ","pages":"Article 102503"},"PeriodicalIF":2.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144865507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}