Knowledge graphs (KGs) play a vital role in intelligent education by offering structured representations of educational content. However, constructing multimodal educational knowledge graphs (EKGs) from diverse open educational resources remains a challenge due to the reliance on costly manual annotations and the lack of multimodal integration. In this work, we propose an automated framework that harnesses the reasoning capabilities of large language models (LLMs) to construct multimodal EKGs from open courses efficiently. In our framework, an Extraction-Verification-Integration-Augmentation pipeline is designed to incrementally extract and refine disciplinary concepts from learning resources. Texts, images, videos and audios are aligned with their corresponding concepts. To ensure semantic consistency across modalities, we propose a cross-modal alignment method based on shared structural and semantic features. Using our framework, we build SciMKG, a large-scale multimodal EKG for Chinese K12 education in sciences (biology, physics, and chemistry), encompassing 1,356 knowledge points, 34,630 multimodal concepts, and 403,400 relational triples. Experimental results show that our method improves concept extraction F1 score by 9 % over state-of-the-art baselines; both automatic and human evaluations confirm the robustness of our multimodal alignment method. SciMKG and our construction toolkit will be publicly released to support further research and applications in AI-driven education.

Multimodal sarcasm detection is a complex task that requires distinguishing subtle complementary signals across modalities while filtering out irrelevant information. Many advanced methods rely on learning shortcuts from datasets rather than extracting intended sarcasm-related features. However, our experiments show that shortcut learning impairs the model's generalization in real-world scenarios. Furthermore, we reveal the weaknesses of current modality fusion strategies for multimodal sarcasm detection through systematic experiments, highlighting the necessity of focusing on effective modality fusion for complex emotion recognition. To address these challenges, we construct MUStARD++R by removing shortcut signals from MUStARD++. Then, a Multimodal Conditional Information Bottleneck (MCIB) model is introduced to enable efficient multimodal fusion for sarcasm detection. Experimental results show that the MCIB achieves the best performance without relying on shortcut learning.

Point-of-Interest (POI) recommendation plays a pivotal role in location-based services by guiding users to discover new and relevant places. While graph-based methods have shown promising results, effectively modeling the diversity and dynamics of user preferences remains a key challenge. Addressing this requires richer representations of both POIs and user interests, as well as more adaptive learning strategies. In this work, we propose TMHKG, a Task-aware Meta-learning framework with a Heterogeneous Knowledge Graph for POI recommendation. To enhance representation learning, TMHKG constructs a dual-view POI knowledge graph that integrates geographical proximity and user-aware category transitions, and models users' evolving interests from sequential visit histories. On top of enriched features, TMHKG adopts a task-aware meta-learning paradigm, treating each user's recommendation task as a separate meta-task. A generalizable recommendation policy is first learned from diverse training tasks and then quickly adapted to each user's unique behavior, enabling highly personalized predictions. Extensive experiments on two real-world datasets demonstrate that TMHKG consistently outperforms state-of-the-art baselines, highlighting its effectiveness in capturing complex user-POI interactions.

Dingling Xu, Ruobing Wang, Qingfei Zhao, Yukun Yan, Zhichun Wang, Daren Zha, Shi Yu, Zhenghao Liu, Shuo Wang, Xu Han, Maosong Sun. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Most of models for machine reading comprehension (MRC) usually focus on recurrent neural networks (RNNs) and attention mechanism, though convolutional neural networks (CNNs) are also involved for time efficiency. However, little attention has been paid to leverage CNNs and RNNs in MRC. For a deeper understanding, humans sometimes need local information for short phrases, sometimes need global context for long passages. In this paper, we propose a novel architecture, i.e., Rception, to capture and leverage both local deep information and global wide context. It fuses different kinds of networks and hyper-parameters horizontally rather than simply stacking them layer by layer vertically. Experiments on the Stanford Question Answering Dataset (SQuAD) show that our proposed architecture achieves good performance.

Knowledge Graph (KG) alignment is to match entities in different KGs, which is important to knowledge fusion and integration. Recently, a number of embedding-based approaches for KG alignment have been proposed and achieved promising results. These approaches first embed entities in low-dimensional vector spaces, and then obtain entity alignments by computations on their vector representations. Although continuous improvements have been achieved by recent work, the performances of existing approaches are still not satisfactory. In this work, we present a new approach that directly learns embeddings of entity-pairs for KG alignment. Our approach first generates a pair-wise connectivity graph (PCG) of two KGs, whose nodes are entity-pairs and edges correspond to relation-pairs; it then learns node (entity-pair) embeddings of the PCG, which are used to predict equivalent relations of entities. To get desirable embeddings, a convolutional neural network is used to generate similarity features of entity-pairs from their attributes; and a graph neural network is employed to propagate the similarity features and get the final embeddings of entity-pairs. Experiments on five real-world datasets show that our approach can achieve the state-of-the-art KG alignment results.

Multilingual knowledge graphs (KGs) such as DBpedia and YAGO contain structured knowledge of entities in several distinct languages, and they are useful resources for cross-lingual AI and NLP applications.Cross-lingual KG alignment is the task of matching entities with their counterparts in different languages, which is an important way to enrich the crosslingual links in multilingual KGs.In this paper, we propose a novel approach for crosslingual KG alignment via graph convolutional networks (GCNs).Given a set of pre-aligned entities, our approach trains GCNs to embed entities of each language into a unified vector space.Entity alignments are discovered based on the distances between entities in the embedding space.Embeddings can be learned from both the structural and attribute information of entities, and the results of structure embedding and attribute embedding are combined to get accurate alignments.In the experiments on aligning real multilingual KGs, our approach gets the best performance compared with other embedding-based KG alignment approaches.

This paper presents our approach for NLPCC 2015 shared task, Entity Recognition and Linking in Chinese Search Queries. The proposed approach takes a query as input, and generates a ranked mention-entity links as results. It combines several different metrics to evaluate the probability of each entity link, including entity relatedness in the given knowledge graph, document similarity between query and the virtual document of entity in the knowledge graph. In the evaluation, our approach gets 33.2 % precision and 65.2 % recall, and ranks the 6th among all the 14 teams according to the average F1-measure.

The vision of Internet of Things is to connect everyday objects through embedding wireless devices, so that they can interact with each other and provide new services. One of major challenges for the IoT is the heterogeneous problem. Information generated by different IoT objects will not be compatible, which hinders data communications between the IoT objects. In this paper, we study semantic technology for integrating heterogeneous information in the IoT. We propose to use ontologies to model the schema of data generated by the IoT objects, and propose a hybrid ontology matching approach to solve the heterogeneous problem. The proposed approach uses multiple matchers to compute similarities between ontology elements, and computes weight for each matcher by making use of the hierarchical structure of ontology. Experimental results show that our method can effectively filter out wrong mappings and obtain alignments with high quality between ontologies.

Wikipedia becomes one of the largest knowledge bases on the Web. It has attracted 513 million page views per day in January 2012. However, one critical issue for Wikipedia is that articles in different language are very unbalanced. For example, the number of articles on Wikipedia in English has reached 3.8 million, while the number of Chinese articles is still less than half million and there are only 217 thousand cross-lingual links between articles of the two languages. On the other hand, there are more than 3.9 million Chinese Wiki articles on Baidu Baike and Hudong.com, two popular encyclopedias in Chinese. One important question is how to link the knowledge entries distributed in different knowledge bases. This will immensely enrich the information in the online knowledge bases and benefit many applications. In this paper, we study the problem of cross-lingual knowledge linking and present a linkage factor graph model. Features are defined according to some interesting observations. Experiments on the Wikipedia data set show that our approach can achieve a high precision of 85.8% with a recall of 88.1%. The approach found 202,141 new cross-lingual links between English Wikipedia and Baidu Baike.

The vision of the Semantic Web is to build a ‘Web of data’ that enables machines to understand the semantics of information on the Web. The Linked Open Data (LOD) project encourages people and organizations to publish various open data sets as Resource Description Framework (RDF) on the Web, which promotes the development of the Semantic Web. Among various LOD datasets, DBpedia has proved a successful structured knowledge base, and has become the central interlinking-hub of the Web of data in English. However, in the Chinese language, there is little linked data published and linked to DBpedia. This hinders the structured knowledge sharing of both Chinese and cross-lingual resources. This paper deals with an approach for building a large-scale Chinese structured knowledge base from Chinese wiki resources, including Hudong and Baidu Baike. The proposed approach first builds an ontology based on the wiki category system and infoboxes, and then extracts instances from wiki articles. Using Hudong as our source, our approach builds an ontology containing 19 542 concepts and 2381 properties. 802 593 instances are extracted and described using the concepts and properties in the extracted ontology and 62 679 of them are linked to equivalent instances in DBpedia. As from Baidu Baike, our approach builds an ontology containing 299 concepts, 37 object properties, and 5590 data type properties. 1 319 703 instances are extracted from Baidu Baike, and 84 343 of them are linked to instances in DBpedia. We provide RDF dumps and SPARQL endpoint to access the established Chinese knowledge bases. The knowledge bases built using our approach can be used not only in Chinese linked data building, but also in many useful applications of large-scale knowledge bases, such as question-answering and semantic search.

The PPV is a robust phase domain macromodel for oscillators. It has been proven to predict oscillators' responses correctly under small signal perturbations, and capture nonlinear phase effects such as injection locking/pulling. In this work, we present a novel approach to extend the PPV macromodel to handle variability in circuit parameters. We derive a modified PPV-based phase equation in which parameter variations are modelled as special inputs. An important feature of our technique is that it avoids PPV re-extraction, this resulting in great convenience and efficiency in its use for, e.g., Monte Carlo type simulations. Using LC and ring oscillators as examples, we demonstrate the capability of the proposed technique for capturing parameter variation effects in injection locking analysis. Simulation results show that our new approach accurately predicts the maximum locking range of oscillators with speedups of two orders of magnitude over direct simulation.