Jeff Z. Pan

AAAI Conference 2026 Conference Paper

MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents

• Yiming Du
• Bingbing Wang
• Yang He
• Bin Liang
• Baojun Wang
• Zhongyang Li
• Lin Gui
• Jeff Z. Pan

Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods prioritise semantic similarity over task intent, degrading multi-session coherence. We propose MemGuide, a two-stage intent-driven memory selection framework: (1) Intent‑Aligned Retrieval retrieves goal-consistent QA‑formatted memory units; (2) Missing‑Slot Guided Filtering reranks units by slot-completion gain via a chain‑of‑thought reasoner and fine‑tuned LLaMA‑8B filter. We also introduce the MS-TOD, the first multi-session TOD benchmark with 132 diverse personas, 956 task goals, and annotated intent-aligned memory targets. Evaluations on MS-TOD show that MemGuide boosts task success rate by 11% (88%→99%) and reduces dialogue length by 2.84 turns, and matches single‑session performance.

AAAI Conference 2026 Conference Paper

ReLUPruner: Rethinking ReLU Importance with Taylor Expansion for Efficient Private Inference

• Zhenpeng Li
• Jinshuo Liu
• Xinyan Wang
• Lina Wang
• Jeff Z. Pan

With the growing adoption of Machine-Learning-As-A-Service (MLaaS), Private Inference (PI) has emerged as a promising solution to address its security concerns through cryptographic techniques. However, nonlinear operations in neural networks account for most of the computational and communication overhead in PI. Existing studies mainly focus on optimizing and reducing the number of ReLU activations in neural networks, but traditional pruning methods may mistakenly remove ReLUs that are critical to maintaining model accuracy. To accurately evaluate the importance of ReLUs in the network, we propose ReLUPruner, a method that uses Taylor expansion to quantify the impact on loss before and after ReLU replacement. Furthermore, we establish a hierarchical importance metric to guide layer-wise ReLU budget allocation and adopt a progressive pruning strategy that dynamically adjust the pruning rate of each layer according to training progress. Extensive experiments on various models and datasets show that ReLUPruner achieves a good balance between ReLU budget and model accuracy, yielding improvements of 1.89% (12.9k ReLUs, CIFAR-10), 3.62% (50k ReLUs, CIFAR-100) and 2.66% (30k ReLUs, Tiny-ImageNet) over the previous state-of-the-art.

AAAI Conference 2026 Conference Paper

Semantic Alignment of Malicious Question Based on Contrastive Semantic Networks and Data Augmentation (Abstract Reprint)

• Xinyan Wang
• Jinshuo Liu
• Juan Deng
• Meng Wang
• Qian Deng
• Youcheng Yan
• Lina Wang
• Yunsong Ma

The identification and filtration of malicious texts in social media environments represent a significant technical challenge aimed at protecting users from online violence and disinformation. This complexity stems from the diversity and innovativeness of social media texts, which include unique expressions and special sentence structures. Particularly, malicious texts in interrogative forms pose alignment challenges with traditional corpora due to existing methods’ failure to exploit the text’s deep global semantic representations. This issue is compounded by the scant research on Chinese texts, leading to inefficiencies in recognition accuracy. To mitigate these challenges, we introduce an innovative framework based on a Global Contrastive Semantic Network (GCSN), designed to enhance malicious text recognition efficiency and accuracy by deeply learning global semantic knowledge. It comprises an encoder for global semantic information modelling and a graph-matching network for semantic similarity evaluation between question pairs, enabling the accurate identification and filtering of malicious texts with complex structures. Furthermore, we introduce a semantic consistency-based data augmentation method (COMBINE), using real-world data to generate balanced positive and negative samples, enriching the dataset and enhancing the model’s ability to distinguish semantic consistency through contrastive learning. Experimental validation on two Chinese datasets demonstrates our model’s exceptional performance, affirming its applicationa value in social media malicious text recognition. Our code is available at https://github.com/Wxy13131313131/GCSN-COMBINE

AAAI Conference 2026 Conference Paper

TaxReasoning: Benchmarking Knowledge-Intensive Mathematical Reasoning with Evolving Tax Laws

• Nan Hu
• Yike Wu
• Jiaye Li
• HuiKang Hu
• Guilin Qi
• Songlin Zhai
• Yongrui Chen
• Tianxing Wu

Recent studies have explored the capabilities of large language models (LLMs) in solving knowledge-intensive mathematical reasoning problems. However, existing benchmarks predominantly involve static theorems that LLMs have encountered during pretraining, failing to assess dynamic knowledge integration. In this work, we introduce TaxReasoning, a novel benchmark designed to evaluate LLMs’ abilities in real-world tax calculation scenarios. These tasks require not only mathematical reasoning and numerical computation, but also the extraction and application of complex, frequently updated tax regulations. Through extensive experiments with state-of-the-art LLMs using diverse prompting strategies and knowledge augmentation techniques, we uncover substantial limitations in their ability to handle dynamic, knowledge-intensive questions—primarily due to missing domain-specific knowledge and ineffective retrieval. Even the best-performing models fall significantly short of human-level performance. Our analysis points to key avenues for improvement, including enhancing LLMs' reasoning capabilities, developing more effective knowledge summarization techniques, and improving retrieval strategies. TaxReasoning offers a critical testbed for advancing LLMs in dynamic knowledge-intensive domains.

AAAI Conference 2026 Conference Paper

Uncovering and Mitigating Transient Blindness in Multimodal Model Editing

• XiaoQi Han
• Ru Li
• Ran Yi
• Hongye Tan
• Zhuomin Liang
• Victor Gutierrez Basulto
• Jeff Z. Pan

Multimodal Model Editing (MMED) aims to correct erroneous knowledge in multimodal models. Existing evaluation methods, adapted from textual model editing, overstate success by relying on low-similarity or random inputs, obscure overfitting. We propose a comprehensive locality evaluation framework, covering three key dimensions: random-image locality, no-image locality, and consistent-image locality, operationalized through seven distinct data types, enabling a detailed and structured analysis of multimodal edits. We introduce De-VQA, a dynamic evaluation for visual question answering, uncovering a phenomenon we term transient blindness, overfitting to edit-similar text while ignoring visuals. Token analysis shows edits disproportionately affect textual tokens. We propose locality-aware adversarial losses to balance cross-modal representations. Empirical results demonstrate that our approach consistently outperforms existing baselines, reducing transient blindness and improving locality by 17% on average.

ECAI Conference 2025 Conference Paper

Decomposing and Revising What Language Models Generate

• Zhichao Yan 0002
• Jiaoyan Chen 0001
• Jiapu Wang
• Xiaoli Li 0001
• Ru Li 0001
• Jeff Z. Pan

Attribution is crucial in question answering (QA) with Large Language Models (LLMs). SOTA question decomposition-based approaches use long form answers to generate questions for retrieving related documents. However, the generated questions are often irrelevant and incomplete, resulting in a loss of facts in retrieval. These approaches also fail to aggregate evidence snippets from different documents and paragraphs. To tackle these problems, we propose a new fact decomposition-based framework called FIDES (faithful context enhanced fact decomposition and evidence aggregation) for attributed QA. FIDES uses a contextually enhanced two-stage faithful decomposition method to decompose long form answers into sub-facts, which are then used by a retriever to retrieve related evidence snippets. If the retrieved evidence snippets conflict with the related sub-facts, such sub-facts will be revised accordingly. Finally, the evidence snippets are aggregated according to the original sentences. Extensive evaluation has been conducted with six datasets, with an additionally proposed new metric called Attrauto–P for evaluating the evidence precision. FIDES outperforms the SOTA methods by over 14% in average with GPT-3. 5-turbo, Gemini and Llama 70B series.

ICLR Conference 2025 Conference Paper

From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal Jungle

• Kaustubh Vyas
• Damien Graux
• Yijun Yang
• Sébastien Montella
• Chenxin Diao
• Wendi Zhou
• Pavlos Vougiouklis
• Ruofei Lai

In response to the call for agent-based solutions that leverage the ever-increasing capabilities of the deep models' ecosystem, we introduce a comprehensive solution for selecting appropriate models and subsequently planning a set of atomic actions to satisfy the end-users' instructions. Our system, Hive, operates over sets of models and, upon receiving natural language instructions, schedules and executes, explainable plans of atomic actions. These actions can involve one or more of the available models to achieve the overall task, while respecting end-users specific constraints. Hive is able to plan complex chains of actions while guaranteeing explainability, using an LLM-based formal logic backbone empowered by PDDL operations. We introduce the MuSE benchmark in order to offer a comprehensive evaluation of the multi-modal capabilities of agent systems. Our findings show that our framework redefines the state-of-the-art for task selection, outperforming other competing systems that plan operations across multiple models while offering transparency guarantees while fully adhering to user constraints.

JAIR Journal 2025 Journal Article

Semantic Alignment of Malicious Question Based on Contrastive Semantic Networks and Data Augmentation

• Xinyan Wang
• Jinshuo Liu
• Juan Deng
• Meng Wang
• Qian Deng
• Youcheng Yan
• Lina Wang
• Yunsong Ma

The identification and filtration of malicious texts in social media environments represent a significant technical challenge aimed at protecting users from online violence and disinformation. This complexity stems from the diversity and innovativeness of social media texts, which include unique expressions and special sentence structures. Particularly, malicious texts in interrogative forms pose alignment challenges with traditional corpora due to existing methods' failure to exploit the text's deep global semantic representations. This issue is compounded by the scant research on Chinese texts, leading to inefficiencies in recognition accuracy. To mitigate these challenges, we introduce an innovative framework based on a Global Contrastive Semantic Network (GCSN), designed to enhance malicious text recognition efficiency and accuracy by deeply learning global semantic knowledge. It comprises an encoder for global semantic information modelling and a graph-matching network for semantic similarity evaluation between question pairs, enabling the accurate identification and filtering of malicious texts with complex structures. Furthermore, we introduce a semantic consistency-based data augmentation method (COMBINE), using real-world data to generate balanced positive and negative samples, enriching the dataset and enhancing the model's ability to distinguish semantic consistency through contrastive learning. Experimental validation on two Chinese datasets demonstrates our model's exceptional performance, affirming its applicationa value in social media malicious text recognition. Our code is available at https://github.com/Wxy13131313131/GCSN-COMBINE

AAAI Conference 2024 Conference Paper

Knowledge-Aware Neuron Interpretation for Scene Classification

• Yong Guan
• Freddy Lécué
• Jiaoyan Chen
• Ru Li
• Jeff Z. Pan

Although neural models have achieved remarkable performance, they still encounter doubts due to the intransparency. To this end, model prediction explanation is attracting more and more attentions. However, current methods rarely incorporate external knowledge and still suffer from three limitations: (1) Neglecting concept completeness. Merely selecting concepts may not sufficient for prediction. (2) Lacking concept fusion. Failure to merge semantically-equivalent concepts. (3) Difficult in manipulating model behavior. Lack of verification for explanation on original model. To address these issues, we propose a novel knowledge-aware neuron interpretation framework to explain model predictions for image scene classification. Specifically, for concept completeness, we present core concepts of a scene based on knowledge graph, ConceptNet, to gauge the completeness of concepts. Our method, incorporating complete concepts, effectively provides better prediction explanations compared to baselines. Furthermore, for concept fusion, we introduce a knowledge graph-based method known as Concept Filtering, which produces over 23% point gain on neuron behaviors for neuron interpretation. At last, we propose Model Manipulation, which aims to study whether the core concepts based on ConceptNet could be employed to manipulate model behavior. The results show that core concepts can effectively improve the performance of original model by over 26%.

AAMAS Conference 2023 Conference Paper

A Web-based Tool for Detecting Argument Validity and Novelty

• Sandrine Chausson
• Ameer Saadat-Yazdi
• Xue Li
• Jeff Z. Pan
• Vaishak Belle
• Nadin Kökciyan
• Björn Ross

Individuals engage in arguments on an everyday basis as they seek to obtain information about current affairs and engage with social media. While fact-checkers are available to help dispel misinformation, it is almost impossible for users to verify every single claim they encounter. This means that oftentimes, it is left to the user to decide whether a claim is well supported. To address this, we have developed a Web interface that allows users to input an argument, and our developed framework automatically detects its validity (soundness of logical deduction) and novelty (whether the argument is non-circular). Our Web-based tool could be used by social media users who wish to evaluate the information they consume. As part of one of the modules developed at the University of Edinburgh, our tool will be deployed as a teaching tool for the students who study argumentation.

AAAI Conference 2023 Conference Paper

DUET: Cross-Modal Semantic Grounding for Contrastive Zero-Shot Learning

• Zhuo Chen
• Yufeng Huang
• Jiaoyan Chen
• Yuxia Geng
• Wen Zhang
• Yin Fang
• Jeff Z. Pan
• Huajun Chen

Zero-shot learning (ZSL) aims to predict unseen classes whose samples have never appeared during training. One of the most effective and widely used semantic information for zero-shot image classification are attributes which are annotations for class-level visual characteristics. However, the current methods often fail to discriminate those subtle visual distinctions between images due to not only the shortage of fine-grained annotations, but also the attribute imbalance and co-occurrence. In this paper, we present a transformer-based end-to-end ZSL method named DUET, which integrates latent semantic knowledge from the pre-trained language models (PLMs) via a self-supervised multi-modal learning paradigm. Specifically, we (1) developed a cross-modal semantic grounding network to investigate the model's capability of disentangling semantic attributes from the images; (2) applied an attribute-level contrastive learning strategy to further enhance the model's discrimination on fine-grained visual characteristics against the attribute co-occurrence and imbalance; (3) proposed a multi-task learning policy for considering multi-model objectives. We find that our DUET can achieve state-of-the-art performance on three standard ZSL benchmarks and a knowledge graph equipped ZSL benchmark. Its components are effective and its predictions are interpretable.

AAAI Conference 2023 Conference Paper

Entity-Agnostic Representation Learning for Parameter-Efficient Knowledge Graph Embedding

• Mingyang Chen
• Wen Zhang
• Zhen Yao
• Yushan Zhu
• Yang Gao
• Jeff Z. Pan
• Huajun Chen

We propose an entity-agnostic representation learning method for handling the problem of inefficient parameter storage costs brought by embedding knowledge graphs. Conventional knowledge graph embedding methods map elements in a knowledge graph, including entities and relations, into continuous vector spaces by assigning them one or multiple specific embeddings (i.e., vector representations). Thus the number of embedding parameters increases linearly as the growth of knowledge graphs. In our proposed model, Entity-Agnostic Representation Learning (EARL), we only learn the embeddings for a small set of entities and refer to them as reserved entities. To obtain the embeddings for the full set of entities, we encode their distinguishable information from their connected relations, k-nearest reserved entities, and multi-hop neighbors. We learn universal and entity-agnostic encoders for transforming distinguishable information into entity embeddings. This approach allows our proposed EARL to have a static, efficient, and lower parameter count than conventional knowledge graph embedding methods. Experimental results show that EARL uses fewer parameters and performs better on link prediction tasks than baselines, reflecting its parameter efficiency.

IJCAI Conference 2023 Conference Paper

Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs

• Mingyang Chen
• Wen Zhang
• Yuxia Geng
• Zezhong Xu
• Jeff Z. Pan
• Huajun Chen

Knowledge graphs (KGs) have become valuable knowledge resources in various applications, and knowledge graph embedding (KGE) methods have garnered increasing attention in recent years. However, conventional KGE methods still face challenges when it comes to handling unseen entities or relations during model testing. To address this issue, much effort has been devoted to various fields of KGs. In this paper, we use a set of general terminologies to unify these methods and refer to them collectively as Knowledge Extrapolation. We comprehensively summarize these methods, classified by our proposed taxonomy, and describe their interrelationships. Additionally, we introduce benchmarks and provide comparisons of these methods based on aspects that are not captured by the taxonomy. Finally, we suggest potential directions for future research.

IJCAI Conference 2022 Conference Paper

Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs

• Zhiwei Hu
• Victor Gutierrez Basulto
• Zhiliang Xiang
• Xiaoli Li
• Ru Li
• Jeff Z. Pan

Multi-hop reasoning over real-life knowledge graphs (KGs) is a highly challenging problem as traditional subgraph matching methods are not capable to deal with noise and missing information. Recently, to address this problem a promising approach based on jointly embedding logical queries and KGs into a low-dimensional space to identify answer entities has emerged. However, existing proposals ignore critical semantic knowledge inherently available in KGs, such as type information. To leverage type information, we propose a novel type-aware model, TypE-aware Message Passing (TEMP), which enhances the entity and relation representation in queries, and simultaneously improves generalization, and deductive and inductive reasoning. Remarkably, TEMP is a plug-and-play model that can be easily incorporated into existing embedding-based models to improve their performance. Extensive experiments on three real-world datasets demonstrate TEMP’s effectiveness.

AAAI Conference 2021 Conference Paper

FL-MSRE: A Few-Shot Learning based Approach to Multimodal Social Relation Extraction

• Hai Wan
• Manrong Zhang
• Jianfeng Du
• Ziling Huang
• Yufei Yang
• Jeff Z. Pan

Social relation extraction (SRE for short), which aims to infer the social relation between two people in daily life, has been demonstrated to be of great value in reality. Existing methods for SRE consider extracting social relation only from unimodal information such as text or image, ignoring the high coupling of multimodal information. Moreover, previous studies overlook the serious unbalance distribution on social relations. To address these issues, this paper proposes FL-MSRE, a few-shot learning based approach to extracting social relations from both texts and face images. Considering the lack of multimodal social relation datasets, this paper also presents three multimodal datasets annotated from four classical masterpieces and corresponding TV series. Inspired by the success of BERT, we propose a strong BERT based baseline to extract social relation from text only. FL-MSRE is empirically shown to outperform the baseline significantly. This demonstrates that using face images benefits text-based SRE. Further experiments also show that using two faces from different images achieves similar performance as from the same image. This means that FL-MSRE is suitable for a wide range of SRE applications where the faces of two people can only be collected from different images. 1

IJCAI Conference 2021 Conference Paper

Knowledge-aware Zero-Shot Learning: Survey and Perspective

• Jiaoyan Chen
• Yuxia Geng
• Zhuo Chen
• Ian Horrocks
• Jeff Z. Pan
• Huajun Chen

Zero-shot learning (ZSL) which aims at predicting classes that have never appeared during the training using external knowledge (a. k. a. side information) has been widely investigated. In this paper we present a literature review towards ZSL in the perspective of external knowledge, where we categorize the external knowledge, review their methods and compare different external knowledge. With the literature review, we further discuss and outlook the role of symbolic knowledge in addressing ZSL and other machine learning sample shortage issues.

KR Conference 2020 Conference Paper

Ontology-guided Semantic Composition for Zero-shot Learning

• Jiaoyan Chen
• Freddy Lécué
• Yuxia Geng
• Jeff Z. Pan
• Huajun Chen

Zero-shot learning (ZSL) is a popular research problem that aims at predicting for those classes that have never appeared in the training stage by utilizing the inter-class relationship with some side information. In this study, we propose to model the compositional and expressive semantics of class labels by an OWL (Web Ontology Language) ontology, and further develop a new ZSL framework with ontology embedding. The effectiveness has been verified by some primary experiments on animal image classification and visual question answering.

AAAI Conference 2020 Conference Paper

Target-Aspect-Sentiment Joint Detection for Aspect-Based Sentiment Analysis

• Hai Wan
• Yufei Yang
• Jianfeng Du
• Yanan Liu
• Kunxun Qi
• Jeff Z. Pan

Aspect-based sentiment analysis (ABSA) aims to detect the targets (which are composed by continuous words), aspects and sentiment polarities in text. Published datasets from SemEval-2015 and SemEval-2016 reveal that a sentiment polarity depends on both the target and the aspect. However, most of the existing methods consider predicting sentiment polarities from either targets or aspects but not from both, thus they easily make wrong predictions on sentiment polarities. In particular, where the target is implicit, i. e. , it does not appear in the given text, the methods predicting sentiment polarities from targets do not work. To tackle these limitations in ABSA, this paper proposes a novel method for target-aspectsentiment joint detection. It relies on a pre-trained language model and can capture the dependence on both targets and aspects for sentiment prediction. Experimental results on the SemEval-2015 and SemEval-2016 restaurant datasets show that the proposed method achieves a high performance in detecting target-aspect-sentiment triples even for the implicit target cases; moreover, it even outperforms the state-of-theart methods for those subtasks of target-aspect-sentiment detection that they are competent to.

IJCAI Conference 2019 Conference Paper

Augmenting Transfer Learning with Semantic Reasoning

• Freddy Lécué
• Jiaoyan Chen
• Jeff Z. Pan
• Huajun Chen

Transfer learning aims at building robust prediction models by transferring knowledge gained from one problem to another. In the semantic Web, learning tasks are enhanced with semantic representations. We exploit their semantics to augment transfer learning by dealing with when to transfer with semantic measurements and what to transfer with semantic embeddings. We further present a general framework that integrates the above measurements and embeddings with existing transfer learning algorithms for higher performance. It has demonstrated to be robust in two real-world applications: bus delay forecasting and air quality forecasting.

NeSy Conference 2019 Conference Paper

Local ABox Consistency Prediction with Transparent TBoxes Using Gated Graph Neural Networks

• Yu Gu 0016
• Jeff Z. Pan
• Gong Cheng 0001
• Heiko Paulheim
• Giorgos Stoilos

AAAI Conference 2019 Conference Paper

Validation of Growing Knowledge Graphs by Abductive Text Evidences

• Jianfeng Du
• Jeff Z. Pan
• Sylvia Wang
• Kunxun Qi
• Yuming Shen
• Yu Deng

This paper proposes a validation mechanism for newly added triples in a growing knowledge graph. Given a logical theory, a knowledge graph, a text corpus, and a new triple to be validated, this mechanism computes a sorted list of explanations for the new triple to facilitate the validation of it, where an explanation, called an abductive text evidence, is a set of pairs of the form (triple, window) where appending the set of triples on the left to the knowledge graph enforces entailment of the new triple under the logical theory, while every sentence window on the right which is contained in the text corpus explains to some degree why the triple on the left is true. From the angle of practice, a special class of abductive text evidences called TEP-based abductive text evidence is proposed, which is constructed from explanation patterns seen before in the knowledge graph. Accordingly, a method for computing the complete set of TEP-based abductive text evidences is proposed. Moreover, a method for sorting abductive text evidences based on distantly supervised learning is proposed. To evaluate the proposed validation mechanism, four knowledge graphs with logical theories are constructed from the four great classical masterpieces of Chinese literature. Experimental results on these datasets demonstrate the efficiency and effectiveness of the proposed mechanism.

KER Journal 2018 Journal Article

A survey of large-scale reasoning on the Web of data

• Grigoris Antoniou
• Sotiris Batsakis
• Raghava Mutharaju
• Jeff Z. Pan
• Guilin Qi
• Ilias Tachmazidis
• Jacopo Urbani
• Zhangquan Zhou

Abstract As more and more data is being generated by sensor networks, social media and organizations, the Web interlinking this wealth of information becomes more complex. This is particularly true for the so-called Web of Data, in which data is semantically enriched and interlinked using ontologies. In this large and uncoordinated environment, reasoning can be used to check the consistency of the data and of associated ontologies, or to infer logical consequences which, in turn, can be used to obtain new insights from the data. However, reasoning approaches need to be scalable in order to enable reasoning over the entire Web of Data. To address this problem, several high-performance reasoning systems, which mainly implement distributed or parallel algorithms, have been proposed in the last few years. These systems differ significantly; for instance in terms of reasoning expressivity, computational properties such as completeness, or reasoning objectives. In order to provide a first complete overview of the field, this paper reports a systematic review of such scalable reasoning approaches over various ontological languages, reporting details about the methods and over the conducted experiments. We highlight the shortcomings of these approaches and discuss some of the open problems related to performing scalable reasoning.

IJCAI Conference 2017 Conference Paper

Learning from Ontology Streams with Semantic Concept Drift

• Jiaoyan Chen
• Freddy Lecue
• Jeff Z. Pan
• Huajun Chen

Data stream learning has been largely studied for extracting knowledge structures from continuous and rapid data records. In the semantic Web, data is interpreted in ontologies and its ordered sequence is represented as an ontology stream. Our work exploits the semantics of such streams to tackle the problem of concept drift i. e. , unexpected changes in data distribution, causing most of models to be less accurate as time passes. To this end we revisited (i) semantic inference in the context of supervised stream learning, and (ii) models with semantic embeddings. The experiments show accurate prediction with data from Dublin and Beijing.

AIJ Journal 2016 Journal Article

Tractable approximate deduction for OWL

• Jeff Z. Pan
• Yuan Ren
• Yuting Zhao

Today's ontology applications require efficient and reliable description logic (DL) reasoning services. Expressive DLs usually have high worst case complexity while tractable DLs are restricted in terms of expressive power. This brings a new challenge: can users use expressive DLs to build their ontologies and still enjoy the efficient services as in tractable languages? Approximation has been considered as a solution to this challenge; however, traditional approximation approaches have limitations in terms of performance and usability. In this paper, we present a tractable approximate reasoning framework for OWL 2 that improves efficiency and guarantees soundness. Evaluation on ontologies from benchmarks and real-world use cases shows that our approach can do reasoning on complex ontologies efficiently with a high recall.

AAAI Conference 2014 Conference Paper

How Long Will It Take? Accurate Prediction of Ontology Reasoning Performance

• Yong-Bin Kang
• Jeff Z. Pan
• Shonali Krishnaswamy
• Wudhichart Sawangphol
• Yuan-Fang Li

For expressive ontology languages such as OWL 2 DL, classification is a computationally expensive task— 2NEXPTIME-complete in the worst case. Hence, it is highly desirable to be able to accurately estimate classification time, especially for large and complex ontologies. Recently, machine learning techniques have been successfully applied to predicting the reasoning hardness category for a given (ontology, reasoner) pair. In this paper, we further develop predictive models to estimate actual classification time using regression techniques, with ontology metrics as features. Our largescale experiments on 6 state-of-the-art OWL 2 DL reasoners and more than 450 significantly diverse ontologies demonstrate that the prediction models achieve high accuracy, good generalizability and statistical significance. Such prediction models have a wide range of applications. We demonstrate how they can be used to efficiently and accurately identify performance hotspots in a large and complex ontology, an otherwise very time-consuming and resource-intensive task.

IJCAI Conference 2013 Conference Paper

Predicting Knowledge in an Ontology Stream

• Freddy Lécué
• Jeff Z. Pan

Recently, ontology stream reasoning has been introduced as a multidisciplinary approach, merging synergies from Artificial Intelligence, Database, World-Wide-Web to reason on semantic augmented data streams. Although knowledge evolution and real-time reasoning have been largely addressed in ontology streams, the challenge of predicting its future (or missing) knowledge remains open and yet unexplored. We tackle predictive reasoning as a correlation and interpretation of past semanticsaugmented data over exogenous ontology streams. Consistent predictions are constructed as Description Logics entailments by selecting and applying relevant cross-streams association rules. The experiments have shown accurate prediction with real and live stream data from Dublin City in Ireland.

AIJ Journal 2008 Journal Article

Natural language directed inference from ontologies

• Chris Mellish
• Jeff Z. Pan

This paper presents an investigation into the problem of content determination in natural language generation (NLG), using as an example the problem of determining what to say when asked “What is an A? ”, where A is a concept defined in an OWL ontology. It is shown that a naive approach to this problem, which just presents a set of the stated axioms, will often inadvertantly violate maxims of cooperative conversation. What is required instead is a kind of inference that generates logical conclusions of the axioms that are suitable for natural language presentation—natural language directed inference (NLDI). Although NLDI, in this case a kind of non-standard inference in description logics, is hard to formalise in general, for this problem we isolate a significant subproblem—that of enumerating subsumers of A that are suitable for natural language presentation. For this problem, which on the face of it appears intractable, we show how factors relevant to natural language presentation enable an optimised solution that is realistic in practice. The paper makes a contribution to the increasingly important practical problem of explaining concepts in an ontology. It also makes a first step towards the development of domain independent principles for content determination.

ECAI Conference 2006 Conference Paper

General Concept Inclusions inFluzzy Description Logics

• Giorgos Stoilos
• Umberto Straccia
• Giorgos Stamou
• Jeff Z. Pan

Fuzzy Description Logics (fuzzy DLs) have been proposed as a language to describe structured knowledge with vague concepts. A major theoretical and computational limitation so far is the inability to deal with General Concept Inclusions (GCIs), which is an important feature of classical DLs. In this paper, we address this issue and develop a calculus for fuzzy DLs with GCIs.

AAAI Conference 2006 Conference Paper

Inconsistencies, Negations and Changes in Ontologies

• Giorgos Flouris
• Jeff Z. Pan

Ontology management and maintenance are considered cornerstone issues in current Semantic Web applications in which semantic integration and ontological reasoning play a fundamental role. The ability to deal with inconsistency and to accommodate change is of utmost importance in realworld applications of ontological reasoning and management, wherein the need for expressing negated assertions also arises naturally. For this purpose, precise, formal definitions of the the different types of inconsistency and negation in ontologies are required. Unfortunately, ontology languages based on Description Logics (DLs) do not provide enough expressive power to represent axiom negations. Furthermore, there is no single, well-accepted notion of inconsistency and negation in the Semantic Web community, due to the lack of a common and solid foundational framework. In this paper, we propose a general framework accounting for inconsistency, negation and change in ontologies. Different levels of negation and inconsistency in DL-based ontologies are distinguished. We demonstrate how this framework can provide a foundation for reasoning with and management of dynamic ontologies.