This paper presents a simple, effective, and cost-efficient strategy, named ModelSwitch, to improve LLM performance by scaling test-time compute. ModelSwitch builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple models, even weaker ones, to leverage their complementary strengths that potentially arise from diverse training data and paradigms. By using sample consistency as a signal, our strategy dynamically switches between models. Theoretical analysis highlights the efficiency and performance advantages of our strategy. Extensive experiments on seven datasets demonstrate that our strategy not only outperforms self-consistency and state-of-the-art multi-agent debate approaches, but also significantly reduces inference costs. Additionally, our strategy requires only a few comparable LLMs to achieve optimal performance and can be extended with verification methods, demonstrating the potential of leveraging multiple LLMs in the generation-verification paradigm.

Semantic parsing, which converts natural language questions into logic forms, plays a crucial role in reasoning within structured environments.However, existing methods encounter two significant challenges: reliance on extensive manually annotated datasets and limited generalization capability to unseen examples.To tackle these issues, we propose Targeted Synthetic Data Generation (TARGA), a practical framework that dynamically generates high-relevance synthetic data without manual annotation.Starting from the pertinent entities and relations of a given question, we probe for the potential relevant queries through layer-wise expansion and cross-layer combination.Then we generate corresponding natural language questions for these constructed queries to jointly serve as the synthetic demonstrations for in-context learning.Experiments on multiple knowledge base question answering (KBQA) datasets demonstrate that TARGA, using only a 7B-parameter model, substantially outperforms existing non-finetuned methods that utilize close-sourced model, achieving notable improvements in F1 scores on GrailQA (+7.7) and KBQA-Agent (+12.2).Furthermore, TARGA also exhibits superior sample efficiency, robustness, and generalization capabilities under non-I.I.D. settings.

Facts extraction is pivotal for constructing knowledge graphs.Recently, the increasing demand for temporal facts in downstream tasks has led to the emergence of the task of temporal fact extraction.In this paper, we specifically address the extraction of temporal facts from natural language text.Previous studies fail to handle the challenge of establishing time-tofact correspondences in complex sentences.To overcome this hurdle, we propose a timelinebased sentence decomposition strategy using large language models (LLMs) with in-context learning, ensuring a fine-grained understanding of the timeline associated with various facts.In addition, we evaluate the performance of LLMs for direct temporal fact extraction and get unsatisfactory results.To this end, we introduce TSDRE 1 , a method that incorporates the decomposition capabilities of LLMs into the traditional fine-tuning of smaller pre-trained language models (PLMs).To support the evaluation, we construct ComplexTRED, a complex temporal fact extraction dataset.Our experiments show that TSDRE achieves state-of-theart results on both HyperRED-Temporal and ComplexTRED datasets.Shaquille O'Neal is one of only three players to win NBA MVP, All-Star game MVP and Finals MVP awards i n the same year (2000); the other players are Willis Reed i n 1970 and Michael Jordan in 1996 and 1998 .

Xiang Huang, Sitao Cheng, Shanshan Huang, Jiayu Shen, Yong Xu, Chaoyun Zhang, Yuzhong Qu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Information retrieval (IR) methods for KGQA consist of two stages: subgraph extraction and answer reasoning. We argue that current subgraph extraction methods underestimate the importance of structural dependencies among evidence facts. We propose Evidence Pattern Retrieval (EPR) to explicitly model the structural dependencies during subgraph extraction. We implement EPR by indexing the atomic adjacency pattern formed by resource pairs. Given a question, we perform dense retrieval to obtain atomic patterns. We then enumerate their combinations to construct candidate evidence patterns. These evidence patterns are scored using a neural model, and the best one is selected to extract a subgraph for downstream answer reasoning. Experimental results demonstrate that the EPR-based approach has significantly improved the F1 scores of IR-KGQA methods by over 10 points on ComplexWebQuestions and achieves competitive performance on WebQuestionsSP.

Although Transformer has achieved success in language and vision tasks, its capacity for knowledge graph (KG) embedding has not been fully exploited. Using the self-attention (SA) mechanism in Transformer to model the subject-relation-object triples in KGs suffers from training inconsistency as SA is invariant to the order of input tokens. As a result, it is unable to distinguish a (real) relation triple from its shuffled (fake) variants (e.g., object-relation-subject) and, thus, fails to capture the correct semantics. To cope with this issue, we propose a novel Transformer architecture, namely, Knowformer, for KG embedding. It incorporates relational compositions in entity representations to explicitly inject semantics and capture the role of an entity based on its position (subject or object) in a relation triple. The relational composition for a subject (or object) entity of a relation triple refers to an operator on the relation and the object (or subject). We borrow ideas from the typical translational and semantic-matching embedding techniques to design relational compositions. We carefully design a residual block to integrate relational compositions into SA and efficiently propagate the composed relational semantics layer by layer. We formally prove that the SA with relational compositions is able to distinguish the entity roles in different positions and correctly capture relational semantics. Extensive experiments and analyses on six benchmark datasets show that Knowformer achieves state-of-the-art performance on both link prediction and entity alignment.

Temporal facts, the facts for characterizing events that hold in specific time periods, are attracting rising attention in the knowledge graph (KG) research communities. In terms of quality management, the introduction of time restrictions brings new challenges to maintaining the temporal consistency of KGs and detecting potential temporal conflicts. Previous studies rely on manually enumerated temporal constraints to detect conflicts, which are labor-intensive and may have granularity issues. We start from the common pattern of temporal facts and constraints and propose a pattern-based temporal constraint mining method, PaTeCon. PaTeCon uses automatically determined graph patterns and their relevant statistical information over the given KG instead of human experts to generate time constraints. Specifically, PaTeCon dynamically attaches type restriction to candidate constraints according to their measuring scores. We evaluate PaTeCon on two large-scale datasets based on Wikidata and Freebase respectively, the experimental results show that pattern-based automatic constraint mining is powerful in generating valuable temporal constraints.

Knowledge base question answering (KBQA) has attracted a lot of interest in recent years, especially for complex questions which require multiple facts to answer. Question decomposition is a promising way to answer complex questions. Existing decomposition methods split the question into sub-questions according to a single compositionality type, which is not sufficient for questions involving multiple compositionality types. In this paper, we propose Question Decomposition Tree (QDT) to represent the structure of complex questions. Inspired by recent advances in natural language generation (NLG), we present a two-staged method called Clue-Decipher to generate QDT. It can leverage the strong ability of NLG model and simultaneously preserve the original questions. To verify that QDT can enhance KBQA task, we design a decomposition-based KBQA system called QDTQA. Extensive experiments show that QDTQA outperforms previous state-of-the-art methods on ComplexWebQuestions dataset. Besides, our decomposition method improves an existing KBQA system by 12% and sets a new state-of-the-art on LC-QuAD 1.0.

Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to answer a question, state-of-the-art methods use a retriever-generator pipeline. However, their retrieval results are static, while different generation steps may rely on different sentences. To attend to the retrieved information that is relevant to each generation step, in this paper, we propose DyRRen, an extended retriever-reranker-generator framework where each generation step is enhanced by a dynamic reranking of retrieved sentences. It outperforms existing baselines on the FinQA dataset.

While question answering over knowledge bases (KBQA) has shown progress in addressing factoid questions, KBQA with numerical reasoning remains relatively unexplored.In this paper, we focus on the complex numerical reasoning in KBQA and propose a new task, NR-KBQA, which necessitates the ability to perform both multi-hop reasoning and numerical reasoning.We design a logic form in Python format called PyQL to represent the reasoning process of numerical reasoning questions.To facilitate the development of NR-KBQA, we present a large dataset called MarkQA, which is automatically constructed from a small set of seeds.Each question in MarkQA is equipped with its corresponding SPARQL query, alongside the step-by-step reasoning process in the QDMR format and PyQL program.Experimental results of some stateof-the-art QA methods on the MarkQA show that complex numerical reasoning in KBQA faces great challenges.2021 2021 value value point in time point in time total assets total assets Netflix Netflix Chappaqua Chappaqua

Graph-structured data describing entities and their properties has become a notable component of the Web. With the increasing size of data graphs, an entity is often associated with too many property values to be entirely shown to the user, thereby requiring a compact but characteristic summary to present its most distinguishing features. This paper aims to automatically generate such characteristic entity summaries for human users. To achieve it, we exploit the informativeness of property values by analyzing the data graph using information theory. To improve the utility of information carried by a summary, we learn it from a text corpus. To reduce the information redundancy of a summary, we perform logical reasoning and measure similarity with statistical support. We formalize the entity summarization problem considering these factors as combinatorial optimization problems to solve. Experiments based on a real data graph and hand-crafted gold standards show that our approach improves on two state-of-the-art approaches in F-measure by 20.63%-38.79%.

Entity alignment—the discovery of identical entities across different knowledge graphs (KGs)—is a critical task in data fusion. In this paper, we revisit existing entity alignment methods in practical and challenging scenarios. Our empirical studies show that current work has a low level of robustness to long-tail entities and the lack of entity names or relation triples. We aim to develop a robust and adaptive entity alignment method, and the availability of relations, attributes, or names is not required. Our method consists of an attribute encoder and a relation encoder, representing an entity by aggregating its attributes or relational neighbors using the attention mechanisms that can highlight the useful attributes and relations in end-to-end learning. To let the encoders complement each other and produce a coherent representation space, we propose adaptive embedding fusion via a gating mechanism. We consider four evaluation settings, i.e., the conventional setting with both relation and attribute triples, as well as three challenging settings without attributes, without relations, without both relations and names, respectively. Results show that our method can achieve state-of-the-art performance. Even in the most challenging setting without relations and names, our method can still achieve promising results while existing methods fail.

The large volume of open data on the Web is expected to be reused and create value. Finding the right data to reuse is a non-trivial task addressed by the recent dataset search systems, which retrieve datasets relevant to a keyword query. An important component of such systems is snippet generation, extracting data from a retrieved dataset to exemplify its content and explain its relevance to the query. Snippet generation algorithms have emerged but were mainly evaluated by user studies. More efficient and reproducible evaluation methods are needed. To meet this challenge, in this article, we present a set of quality metrics for assessing the usefulness of a snippet from different perspectives, and we select and aggregate them into quality profiles for different stages of a dataset search process. Furthermore, we create a benchmark from thousands of collected real-world data needs and datasets, on which we apply the presented quality metrics and profiles to evaluate snippets generated by two existing algorithms and three adapted algorithms. The results, which are reproducible as they are automatically computed without human interaction, show the pros and cons of the tested algorithms and highlight directions for future research. The benchmark data is publicly available.

Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text.Conventional neural models are insufficient for logical reasoning, while symbolic reasoners cannot directly apply to text.To meet the challenge, we present a neural-symbolic approach which, to predict an answer, passes messages over a graph representing logical relations between text units.It incorporates an adaptive logic graph network (AdaLoGN) which adaptively infers logical relations to extend the graph and, essentially, realizes mutual and iterative reinforcement between neural and symbolic reasoning.We also implement a novel subgraph-to-node message passing mechanism to enhance context-option interaction for answering multiple-choice questions.Our approach shows promising results on ReClor and LogiQA.

Question answering over knowledge bases (KBQA) for complex questions is a challenging task in natural language processing. Recently, generation-based methods that translate natural language questions to executable logical forms have achieved promising performance. These methods use auxiliary information to augment the logical form generation of questions with unseen KB items or novel combinations, but the noise introduced can also leads to more incorrect results. In this work, we propose GMT-KBQA, a Generation-based KBQA method via Multi-Task learning, to better retrieve and utilize auxiliary information. GMT-KBQA first obtains candidate entities and relations through dense retrieval, and then introduces a multi-task model which jointly learns entity disambiguation, relation classification, and logical form generation. Experimental results show that GMT-KBQA achieves state-of-the-art results on both ComplexWebQuestions and WebQuestionsSP datasets. Furthermore, the detailed evaluation demonstrates that GMT-KBQA benefits from the auxiliary tasks and has a strong generalization capability.

Answering factual questions with temporal intent over knowledge graphs (temporal KGQA) attracts rising attention in recent years.In the generation of temporal queries, existing KGQA methods ignore the fact that some intrinsic connections between events can make them temporally related, which may limit their capability.We systematically analyze the possible interpretation of temporal constraints and conclude the interpretation structures as the Semantic Framework of Temporal Constraints, SF-TCons.Based on the semantic framework, we propose a temporal question answering method, SF-TQA, which generates query graphs by exploring the relevant facts of mentioned entities, where the exploring process is restricted by SF-TCons.Our evaluations show that SF-TQA significantly outperforms existing methods on two benchmarks over different knowledge graphs.

Pre-trained language models (PLMs) have shown their effectiveness in multiple scenarios.However, KBQA remains challenging, especially regarding coverage and generalization settings.This is due to two main factors: i) understanding the semantics of both questions and relevant knowledge from the KB; ii) generating executable logical forms with both semantic and syntactic correctness.In this paper, we present a new KBQA model, TIARA, which addresses those issues by applying multi-grained retrieval to help the PLM focus on the most relevant KB contexts, viz., entities, exemplary logical forms, and schema items.Moreover, constrained decoding is used to control the output space and reduce generation errors.Experiments over important benchmarks demonstrate the effectiveness of our approach.TIARA outperforms previous SOTA, including those using PLMs or oracle entity annotations, by at least 4.1 and 1.1 F1 points on GrailQA and WebQuestionsSP, respectively.Specifically on GrailQA, TIARA outperforms previous models in all categories, with an improvement of 4.7 F1 points in zero-shot generalization. 1

Given a large graph representing relations between entities, searching for complex relationships (called semantic associations, or SAs for short) between a set of entities is a common type of information needs in many domains. Further, numerous SAs are often abstracted into a few frequent high-level conceptual graph patterns (called SA patterns, or SAPs for short), which organize SAs into interpretable subgroups. Whereas the quality and usefulness of SAs and SAPs have been extensively studied in the literature, in this article we aim to develop faster algorithms for SA search and frequent SAP mining. For the former problem, we leverage distances to prune the search space, and implement a distance oracle to balance the time and space for distance calculation. For the latter problem, we exploit both graph structure and labels to induce fine-grained skeleton-based partitions of SAs, which may be pruned to reduce SAP enumeration. Besides, we generate canonical codes for SAs, which not only enable result deduplication but also are reused in SAP mining to improve the overall performance. We extensively evaluate the efficiency of our algorithms on four large graphs, using both random queries and simulated queries which reproduce the extreme case of finding numerous SAs.

Graph neural networks (GNNs) have emerged as a powerful paradigm for embedding-based entity alignment due to their capability of identifying isomorphic subgraphs. However, in real knowledge graphs (KGs), the counterpart entities usually have non-isomorphic neighborhood structures, which easily causes GNNs to yield different representations for them. To tackle this problem, we propose a new KG alignment network, namely AliNet, aiming at mitigating the non-isomorphism of neighborhood structures in an end-to-end manner. As the direct neighbors of counterpart entities are usually dissimilar due to the schema heterogeneity, AliNet introduces distant neighbors to expand the overlap between their neighborhood structures. It employs an attention mechanism to highlight helpful distant neighbors and reduce noises. Then, it controls the aggregation of both direct and distant neighborhood information using a gating mechanism. We further propose a relation loss to refine entity representations. We perform thorough experiments with detailed ablation studies and analyses on five entity alignment datasets, demonstrating the effectiveness of AliNet.

Semantic parsing transforms a natural language question into a formal query over a knowledge base. Many existing methods rely on syntactic parsing like dependencies. However, the accuracy of producing such expressive formalisms is not satisfying on long complex questions. In this paper, we propose a novel skeleton grammar to represent the high-level structure of a complex question. This dedicated coarse-grained formalism with a BERT-based parsing algorithm helps to improve the accuracy of the downstream fine-grained semantic parsing. Besides, to align the structure of a question with the structure of a knowledge base, our multi-strategy method combines sentence-level and word-level semantics. Our approach shows promising performance on several datasets.

Knowledge bases (KBs) store rich yet heterogeneous entities and facts. Entity resolution (ER) aims to identify entities in KBs which refer to the same real-world object. Recent studies have shown significant benefits of involving humans in the loop of ER. They often resolve entities with pairwise similarity measures over attribute values and resort to the crowds to label uncertain ones. However, existing methods still suffer from high labor costs and insufficient labeling to some extent. In this paper, we propose a novel approach called crowdsourced collective ER, which leverages the relationships between entities to infer matches jointly rather than independently. Specifically, it iteratively asks human workers to label picked entity pairs and propagates the labeling information to their neighbors in distance. During this process, we address the problems of candidate entity pruning, probabilistic propagation, optimal question selection and error-tolerant truth inference. Our experiments on real-world datasets demonstrate that, compared with state-of-the-art methods, our approach achieves superior accuracy with much less labeling.

Recognizing time expressions is a fundamental and important task in many applications of natural language understanding, such as reading comprehension and question answering. Several newest state-of-the-art approaches have achieved good performance on recognizing time expressions. These approaches are black-boxed or based on heuristic rules, which leads to the difficulty in understanding the temporal information. On the contrary, classic rule-based or semantic parsing approaches can capture rich structural information, but their performances on recognition are not so good. In this paper, we propose a pattern-based approach, called PTime, which automatically generates and selects patterns for recognizing time expressions. In this approach, time expressions in training text are abstracted into type sequences by using fine-grained token types, thus the problem is transformed to select an appropriate subset of the sequential patterns. We use the Extended Budgeted Maximum Coverage (EBMC) model to optimize the pattern selection. The main idea is to maximize the correct token sequences matched by the selected patterns while the number of the mistakes should be limited by an adjustable budget. The interpretability of patterns and the adjustability of permitted number of mistakes make PTime a very promising approach for many applications. Experimental results show that PTime achieves a very competitive performance as compared with existing state-of-the-art approaches.

Reusing published datasets on the Web is of great interest to researchers and developers. Their data needs may be met by submitting queries to a dataset search engine to retrieve relevant datasets. In this ongoing work towards developing a more usable dataset search engine, we characterize real data needs by annotating the semantics of 1,947 queries using a novel fine-grained scheme, to provide implications for enhancing dataset search. Based on the findings, we present a query-centered framework for dataset search, and explore the implementation of snippet generation and evaluate it with a preliminary user study.

Knowledge graphs (KGs) have been extensively used to annotate text, e.g., news articles, in order to enhance its comprehension by readers. This requires to map entities occurring in the news to the target entities of the KG and to extract a so-called relationship sub-graph (RSG) that spans these entities. RSG extraction is computationally demanding and cannot scale to large KGs. Existing approximation algorithms that focus on structurally compact RSGs are not satisfactory since they often return no answers. We address this problem and develop an efficient algorithm to find approximations that connect the most salient subset of the target entities. Moreover, we propose a context-aware method to rank RSGs by their relevance to the news and their semantic cohesion. In the demo we will present our approach and the attendees will be able to experience how our system MiCRon helps to make sense of news article by computing and presenting RSGs relevant to these articles.

Jiwei Ding, Wei Hu, Qixin Xu, Yuzhong Qu. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Zixian Huang, Yulin Shen, Xiao Li, Yu’ang Wei, Gong Cheng, Lin Zhou, Xinyu Dai, Yuzhong Qu. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

We study the problem of embedding-based entity alignment between knowledge graphs (KGs). Previous works mainly focus on the relational structure of entities. Some further incorporate another type of features, such as attributes, for refinement. However, a vast of entity features are still unexplored or not equally treated together, which impairs the accuracy and robustness of embedding-based entity alignment. In this paper, we propose a novel framework that unifies multiple views of entities to learn embeddings for entity alignment. Specifically, we embed entities based on the views of entity names, relations and attributes, with several combination strategies. Furthermore, we design some cross-KG inference methods to enhance the alignment between two KGs. Our experiments on real-world datasets show that the proposed framework significantly outperforms the state-of-the-art embedding-based entity alignment methods. The selected views, cross-KG inference and combination strategies all contribute to the performance improvement.

Relevance search over a knowledge graph (KG) has gained much research attention. Given a query entity in a KG, the problem is to find its most relevant entities. However, the relevance function is hidden and dynamic. Different users for different queries may consider relevance from different angles of semantics. The ambiguity in a query is more noticeable in the presence of thousands of types of entities and relations in a schema-rich KG, which has challenged the effectiveness and scalability of existing methods. To meet the challenge, our approach called RelSUE requests a user to provide a small number of answer entities as examples, and then automatically learns the most likely relevance function from these examples. Specifically, we assume the intent of a query can be characterized by a set of meta-paths at the schema level. RelSUE searches a KG for diversified significant meta-paths that best characterize the relevance of the user-provided examples to the query entity. It reduces the large search space of a schema-rich KG using distance and degree-based heuristics, and performs reasoning to deduplicate meta-paths that represent equivalent query-specific semantics. Finally, a linear model is learned to predict meta-path based relevance. Extensive experiments demonstrate that RelSUE outperforms several state-of-the-art methods.

Triple-structured open data creates value in many ways. However, the reuse of datasets is still challenging. Users feel difficult to assess the usefulness of a large dataset containing thousands or millions of triples. To satisfy the needs, existing abstractive methods produce a concise high-level abstraction of data. Complementary to that, we adopt the extractive strategy and aim to select the optimum small subset of data from a dataset as a snippet to compactly illustrate the content of the dataset. This has been formulated as a combinatorial optimization problem in our previous work. In this article, we design a new algorithm for the problem, which is an order of magnitude faster than the previous one but has the same approximation ratio. We also develop an anytime algorithm that can generate empirically better solutions using additional time. To suit datasets that are partially accessible via online query services (e.g., SPARQL endpoints for RDF data), we adapt our algorithms to trade off quality of snippet for feasibility and efficiency in the Web environment. We carry out extensive experiments based on real RDF datasets and SPARQL endpoints for evaluating quality and running time. The results demonstrate the effectiveness and practicality of our proposed algorithms.

Complex questions in reading comprehension tasks require integrating information from multiple sentences. In this work, to answer such questions involving temporal and causal relations, we generate event graphs from text based on dependencies, and rank answers by aligning event graphs. In particular, the alignments are constrained by graph-based reasoning to ensure temporal and causal agreement. Our focused approach self-adaptively complements existing solutions; it is automatically triggered only when applicable. Experiments on RACE and MCTest show that state-of-the-art methods are notably improved by using our approach as an add-on.

Searching for associations between entities is needed in many domains. It has been facilitated by the emergence of graph-structured semantic data on the Web, which offers structured semantic associations more explicit than those hiding in unstructured text for computers to discover. The increasing volume of semantic data requires ranking techniques to identify the more important semantic associations for users. Considering a lack of comprehensive empirical evaluation of existing techniques, we carry out an extensive evaluation of eight techniques including two novel ones we propose. The practical effectiveness of these techniques is assessed based on 1,200 ground-truth rankings created by 30 human experts for real-life semantic associations and on the explanations given by the experts.

Embedding-based entity alignment represents different knowledge graphs (KGs) as low-dimensional embeddings and finds entity alignment by measuring the similarities between entity embeddings. Existing approaches have achieved promising results, however, they are still challenged by the lack of enough prior alignment as labeled training data. In this paper, we propose a bootstrapping approach to embedding-based entity alignment. It iteratively labels likely entity alignment as training data for learning alignment-oriented KG embeddings. Furthermore, it employs an alignment editing method to reduce error accumulation during iterations. Our experiments on real-world datasets showed that the proposed approach significantly outperformed the state-of-the-art embedding-based ones for entity alignment. The proposed alignment-oriented KG embedding, bootstrapping process and alignment editing method all contributed to the performance improvement.

Entity resolution (ER), the process of identifying entities that refer to the same real-world object, has long been studied in the knowledge graph (KG) community, among many others. Humans, as a valuable source of background knowledge, are increasingly getting involved in this loop by crowdsourcing and active learning, where presenting condensed and easily-compared information is vital to help human intervene in an ER task. However, current methods for single entity or pairwise summarization cannot well support humans to observe and compare multiple entities simultaneously, which impairs the efficiency and accuracy of human intervention. In this paper, we propose an automated approach to select a few important properties and values for a set of entities, and assemble them by a comparative table. We formulate several optimization problems for generating an optimal comparative table according to intuitive goodness measures and various constraints. Our experiments on real-world datasets, comparison with related work and user study demonstrate the superior efficiency, precision and user satisfaction of our approach in multi-entity resolution (MER).

Properties are used to describe entities, and a part of them are likely to be clustered together to constitute an aspect. For example, first name, middle name and last name are usually gathered to describe a person's name. However, existing automated approaches to property clustering remain far from satisfactory for an open domain like Linked Data. In this paper, the authors firstly investigated the relatedness between properties using 13 different measures. Then, they employed seven clustering algorithms and two combination methods for property clustering. Based on a sample set of Linked Data, the authors empirically studied property clustering in Linked Data and found that a proper combination of different measures and clustering algorithms gave rise to the best result. Additionally, they reported how property clustering can improve user experience in an entity browsing system.

To embrace the open data movement, increasingly many datasets have been published on the Web to be reused. Users, when assessing the usefulness of an unfamiliar dataset, need means to quickly inspect its contents. To satisfy the needs, we propose to automatically extract an optimal small portion from a dataset, called a snippet, to concisely illustrate the contents of the dataset. We consider the quality of a snippet from three aspects: coverage, familiarity, and cohesion, which are jointly formulated in a new combinatorial optimization problem called the maximum-weight-and-coverage connected graph problem (MwcCG). We give a constant-factor approximation algorithm for this NP-hard problem, and experiment with our solution on real-world datasets. Our quantitative analysis and user study show that our approach outperforms a baseline approach.

Searching for associations between entities is needed in many domains like national security and bioinformatics. In recent years, it has been facilitated by the emergence of graph-structured semantic data on the Web, which offers structured semantic associations more explicit than those hiding in unstructured text for computers to discover. The increasing volume of semantic data often produces excessively many semantic associations, and requires ranking techniques to identify the more important ones for users. Despite the fruitful theoretical research on innovative ranking techniques, there is a lack of comprehensive empirical evaluation of these techniques. In this article, we carry out an extensive evaluation of eight techniques for ranking semantic associations, including two novel ones we propose. The practical effectiveness of these techniques is assessed based on 1,200 ground-truth rankings created by 30 human experts for real-life semantic associations and the explanations given by the experts. Our findings also suggest a number of directions in improving existing techniques and developing novel techniques for future work.

While the geographical domain has long been involved as an important part of the Linked Data, the small amount of Chinese linked geographical data impedes the integration and sharing of both Chinese and cross-lingual knowledge. In this paper, we contribute to the development of a new Chinese linked geographical dataset named Clinga, by obtaining data from the largest Chinese wiki encyclopedia. We manually design a new geography ontology to categorize a wide range of physical and human geographical entities, and carry out an automatic discovery of links to existing knowledge bases. The resulted dataset contains over half million Chinese geographical entities and is open access.

The quantity of entities in the Linked Data is increasing rapidly. For entity search and browsing systems, filtering is very useful for users to find entities that they are interested in. Type is a kind of widely-used facet and can be easily obtained from knowledge bases, which enables to create filters by selecting at most K types of an entity collection. However, existing approaches often fail to select high-quality type filters due to complex overlap between types. In this paper, we propose a novel type selection approach based upon Budgeted Maximum Coverage (BMC), which can achieve integral optimization for the coverage quality of type filters. Furthermore, we define a new optimization problem called Extended Budgeted Maximum Coverage (EBMC) and propose an EBMC-based approach, which enhances the BMC-based approach by incorporating the relevance between entities and types, so as to create sensible type filters. Our experimental results show that the EBMC-based approach performs best comparing with several representative approaches.

Entity linking connects the Web of documents with knowledge bases. It is the task of linking an entity mention in text to its corresponding entity in a knowledge base. Whereas a large body of work has been devoted to automatically generating candidate entities, or ranking and choosing from them, manual efforts are still needed, e.g., for defining gold-standard links for evaluating automatic approaches, and for improving the quality of links in crowdsourcing approaches. However, structured descriptions of entities in knowledge bases are sometimes very long. To avoid overloading human users with too much information and help them more efficiently choose an entity from candidates, we aim to substitute entire entity descriptions with compact, equally effective structured summaries that are automatically generated. To achieve it, our approach analyzes entity descriptions in the knowledge base and the context of entity mention from multiple perspectives, including characterizing and differentiating power, information overlap, and relevance to context. Extrinsic evaluation (where human users carry out entity linking tasks) and intrinsic evaluation (where human users rate summaries) demonstrate that summaries generated by our approach help human users carry out entity linking tasks more efficiently (22-23% faster), without significantly affecting the quality of links obtained; and our approach outperforms existing approaches to summarizing entity descriptions.

Many ontologies have been published on the Semantic Web, to be shared to describe resources. Among them, large ontologies of real-world areas have the scalability problem in presenting semantic technologies such as ontology matching (OM). This either suffers from too long run time or has strong hypotheses on the running environment. To deal with this issue, we propose a three-stage MapReduce-based approach V-Doc + for matching large ontologies, based on the MapReduce framework and virtual document technique. Specifically, two MapReduce processes are performed in the first stage to extract the textual descriptions of named entities (classes, properties, and instances) and blank nodes, respectively. In the second stage, the extracted descriptions are exchanged with neighbors in Resource Description Framework (RDF) graphs to construct virtual documents. This extraction process also benefits from the MapReduce-based implementation. A word-weight-based partitioning method is proposed in the third stage to conduct parallel similarity calculation using the term frequency-inverse document frequency (TF-IDF) model. Experimental results on two large-scale real datasets and the benchmark testbed from Ontology Alignment Evaluation Initiative (OAEI) are reported, showing that the proposed approach significantly reduces the run time with minor loss in precision and recall.

Ontology reasoning and reasoning-based search expansion are powerful tools for semantic applications. In this paper, we investigate how to apply ontology reasoning, with different ontology metamodeling approaches, to diagnose software models, in particular on models with multiple levels software models, in particular on models with multiple levels of abstraction.

An object on the Semantic Web is likely to be denoted with multiple URIs by different parties. Object coreference resolution is to identify "equivalent" URIs that denote the same object. Driven by the Linking Open Data (LOD) initiative, millions of URIs have been explicitly linked with owl:sameAs statements, but potentially coreferent ones are still considerable. Existing approaches address the problem mainly from two directions: one is based upon equivalence inference mandated by OWL semantics, which finds semantically coreferent URIs but probably omits many potential ones; the other is via similarity computation between property-value pairs, which is not always accurate enough. In this paper, we propose a self-training approach for object coreference resolution on the Semantic Web, which leverages the two classes of approaches to bridge the gap between semantically coreferent URIs and potential candidates. For an object URI, we firstly establish a kernel that consists of semantically coreferent URIs based on owl:sameAs, (inverse) functional properties and (max-)cardinalities, and then extend such kernel iteratively in terms of discriminative property-value pairs in the descriptions of URIs. In particular, the discriminability is learnt with a statistical measurement, which not only exploits key characteristics for representing an object, but also takes into account the matchability between properties from pragmatics. In addition, frequent property combinations are mined to improve the accuracy of the resolution. We implement a scalable system and demonstrate that our approach achieves good precision and recall for resolving object coreference, on both benchmark and large-scale datasets.

Web ontologies provide shared concepts for describing domain entities and thus enable semantic interoperability between applications. To facilitate concept sharing and ontology reusing, we developed Falcons Concept Search, a novel keyword-based ontology search engine. In this paper, we illustrate how the proposed mode of interaction helps users quickly find ontologies that satisfy their needs and present several supportive techniques including a new method of constructing virtual documents of concepts for keyword search, a popularity-based scheme to rank concepts and ontologies, and a way to generate query-relevant structured snippets. We also report the results of a usability evaluation as well as user feedback.

Falconer is a semantic Web search engine enhanced SIOC (Semantically-Interlinked Online Communities) application, which is designed to demonstrate the ability of accelerating the creation and reuse process of semantic Web data with easy-to-use user interfaces. In this process, semantic Web search engines feed existing semantic data into the SIOC framework, where new semantic data are composed by the community and indexed again by those search engines. Compared to existing social (semantic) Web applications, Falconer inherently conforms to SIOC specification. It provides semantic search engine based user registration suggestion, friends auto-discovery, and semantic annotation for forum post content. Another distinctive feature is that it enables users to subscribe any resource having a URI as the topic they are interested in. The relationships among users, topics, and posts are further visualized for analyzing the topic trends in the community. As all semantic data are formatted in RDF and RDFa, they can be queried with SPARQL query language.

Along with the rapid growth of the data Web, searching linked objects for information needs and for reusing become emergent for ordinary Web users and developers, respectively. To meet the challenge, we present Falcons Object Search, a keyword-based search engine for linked objects. To serve various keyword queries, for each object the system constructs a comprehensive virtual document including not only associated literals but also the textual descriptions of associated links and linked objects. The resulting objects are ranked by considering both their relevance to the query and their popularity. For each resulting object, a query-relevant structured snippet is provided to show the associated literals and linked objects matched with the query. Besides, Web-scale class-inclusion reasoning is performed to discover implicit typing information, and users could navigate class hierarchies for incremental class-based results filtering. The results of a task-based experiment show the promising features of the system.

This paper introduces dynamic view, a novel semantic Web application, for users to query, browse and visualize distribution and evolution of research interests in temporal, spatial and ontological dimensions. We present motivation and requirements for a system like dynamic view, and discuss its architecture. We outline main algorithms for term extraction from Web pages of researchers and ontology learning from digital libraries, and sketch visualizations we used in the interface.

As of today, the amount of data on the Semantic Web has grown considerably. The services for searching and browsing entities on the Semantic Web are in demand. To provide such services, we developed the Falcons system. In this poster, we present the features of the Falcons system.

Ontology summarization is very important to quick understanding and selection of ontologies. In this paper, we study extractive summarization of ontology. We propose a notion of RDF sentence as the basic unit of summarization. An RDF Sentence Graph is proposed to characterize the links between RDF sentences derived from a given ontology. The salience of each RDF sentence is assessed in terms of its "centrality" in the graph. We propose to summarize an ontology by extracting a set of salient RDF sentences according to a re-ranking strategy. We compare several measurements in assessing the salience of RDF sentences and give an overall evaluation of experiment results, which shows that our approach to ontology summarization is feasible.

On the investigation of linguistic techniques used in ontology matching, we propose a new idea of virtual documents to pursue a cost-effective approach to linguistic matching in this paper. Basically, as a collection of weighted words, the virtual document of a URIref declared in an ontology contains not only the local descriptions but also the neighboring information to reflect the intended meaning of the URIref. Document similarity can be computed by traditional vector space techniques, and then be used in the similaritybased approaches to ontology matching. In particular, the RDF graph structure is exploited to define the description formulations and the neighboring operations. Experimental results show that linguistic matching based on the virtual documents is dominant in average F-Measure as compared to other three approaches. It is also demonstrated by our experiments that the virtual documents approach is cost-effective as compared to other linguistic matching approaches.