Search

Multi-hop reasoning over paths in knowledge graphs has attracted rising research interest in the field of knowledge graph completion. Entity types and relation types both contain various kinds of information content though only a subset of them are helpful in the specific triples. Although significant progress has been made by existing models, they have two major shortcomings. First, these models seldom learn an explicit representation of entities and relations with semantic information. Second, they reason without discriminating distinct role types that the same entity with multiple types plays in different triples. To address these issues, we develop a novel path-based reasoning with constrained type attention model, which tries to identify entity types by leveraging relation type constraints in the corresponding triples. Our experimental evaluation shows that the proposed model outperforms the state of the art on a real-world dataset. Further analyses also confirm that both word-level and triple-level attention mechanisms of our model are effective.

Heterogeneous information networks (HINs) have been ubiquitous in the real-world. HIN embeddings, which encode various information of the networks into low-dimensional vectors, can facilitate a wide range of applications on graph-structured data. Existing HIN embedding methods include random walk based methods that may not fully utilize the edge semantics and knowledge graph embedding methods that restrict the expression ability of topological information. In this paper, we propose a novel adaptive embedding framework, which integrates these two kinds of methods to preserve both topological information and relational information. By incorporating an assistant knowledge graph embedding model, the proposed framework performs efficient biased random walk under the guidance of edge semantics.

Background The available antibiotic decision-making systems were developed from a physician’s perspective. However, because infectious diseases are common, many patients desire access to knowledge via a search engine. Although the use of antibiotics should, in principle, be subject to a doctor’s advice, many patients take them without authorization, and some people cannot easily or rapidly consult a doctor. In such cases, a reliable antibiotic prescription support system is needed. Methods and results This study describes the construction and optimization of the sensitivity and specificity of a decision support system named IDDAP, which is based on ontologies for infectious disease diagnosis and antibiotic therapy. The ontology for this system was constructed by collecting existing ontologies associated with infectious diseases, syndromes, bacteria and drugs into the ontology's hierarchical conceptual schema. First, IDDAP identifies a potential infectious disease based on a patient’s self-described disease state. Then, the system searches for and proposes an appropriate antibiotic therapy specifically adapted to the patient based on factors such as the patient’s body temperature, infection sites, symptoms/signs, complications, antibacterial spectrum, contraindications, drug–drug interactions between the proposed therapy and previously prescribed medication, and the route of therapy administration. The constructed domain ontology contains 1,267,004 classes, 7,608,725 axioms, and 1,266,993 members of “SubClassOf” that pertain to infectious diseases, bacteria, syndromes, anti-bacterial drugs and other relevant components. The system includes 507 infectious diseases and their therapy methods in combination with 332 different infection sites, 936 relevant symptoms of the digestive, reproductive, neurological and other systems, 371 types of complications, 838,407 types of bacteria, 341 types of antibiotics, 1504 pairs of reaction rates (antibacterial spectrum) between antibiotics and bacteria, 431 pairs of drug interaction relationships and 86 pairs of antibiotic-specific population contraindicated relationships. Compared with the existing infectious disease-relevant ontologies in the field of knowledge comprehension, this ontology is more complete. Analysis of IDDAP's performance in terms of classifiers based on receiver operating characteristic (ROC) curve results (89.91%) revealed IDDAP's advantages when combined with our ontology. Conclusions and significance This study attempted to bridge the patient/caregiver gap by building a sophisticated application that uses artificial intelligence and machine learning computational techniques to perform data-driven decision-making at the point of primary care. The first level of decision-making is conducted by the IDDAP and provides the patient with a first-line therapy. Patients can then make a subjective judgment, and if any questions arise, should consult a physician for subsequent decisions, particularly in complicated cases or in cases in which the necessary information is not yet available in the knowledge base.

Distant supervision based methods for entity and relation extraction have received increasing popularity due to the fact that these methods require light human annotation efforts. In this paper, we consider the problem of \textit{shifted label distribution}, which is caused by the inconsistency between the noisy-labeled training set subject to external knowledge graph and the human-annotated test set, and exacerbated by the pipelined entity-then-relation extraction manner with noise propagation. We propose a joint extraction approach to address this problem by re-labeling noisy instances with a group of cooperative multiagents. To handle noisy instances in a fine-grained manner, each agent in the cooperative group evaluates the instance by calculating a continuous confidence score from its own perspective; To leverage the correlations between these two extraction tasks, a confidence consensus module is designed to gather the wisdom of all agents and re-distribute the noisy training set with confidence-scored labels. Further, the confidences are used to adjust the training losses of extractors. Experimental results on two real-world datasets verify the benefits of re-labeling noisy instance, and show that the proposed model significantly outperforms the state-of-the-art entity and relation extraction methods., Accepted by ACL 2020

Textual entailment is a central problem of language variability, which has been attracting a lot of interest and it poses significant issues in front of systems aimed at natural language understanding. Recently, various frameworks have been proposed for textual entailment recognition, ranging from traditional computational linguistics techniques to deep learning model based methods. However, recent deep neural networks that achieve the state of the art on textual entailment task only consider the context information of the given sentences rather than the real-world background information and knowledge beyond the context. In the paper, we propose a Knowledge-Context Interactive Textual Entailment Network (KCI-TEN) that learns graph level sentence representations by harnessing external knowledge graph with graph attention network. We further propose a text-graph interaction mechanism for neural based entailment matching learning, which endows the redundancy and noise with less importance and put emphasis on the informative representations. Experiments on the SciTail dataset demonstrate that KCI-TEN outperforms the state-of-the-art methods.

Daily sale prediction is an essential step for industries to control inventory and reduce economic loss. In the past, it has been estimated using Kalman filter, with the restriction of linearity and Gaussian. In this study, a model combining parallel Sampling Importance Resampling Filter with an interacting multiple model is utilized to predict the future daily sale of products. The methodology is tested over a sale record of 80 products of a local online retailer in the past 400 days. The data of the last 30 days are used to verify the accuracy. Our experiments indicate that: 1) 29.33% of predicted values produced by the proposed method are within 10% fluctuation of true inventory data; (2) Better accuracy and efficacy can be achieved if either interacting multiple-model with different noise variances or parallel Sampling Importance Resampling Filter is applied; (3) Combination of the above two methods with suitable parameter settings may generate better performance, compared to the cases where only one of them is applied.

Knowledge Based Question Answering (KBQA) is one of the most promising approaches to provide suitable answers for the queries posted by users. Relation detection that aims to take full advantage of the substantial knowledge contained in knowledge base (KB) becomes increasingly important. Significant progress has been made in performing relation detection over KB. However, recent deep neural networks that achieve the state of the art on KB-based relation detection task only consider the context information of question sentences rather than the relatedness between question and answer candidates, and exclusively extract the relation from KB triple rather than learn informative relational path. In this paper, we propose a Knowledge-driven Relation Detection network (KRD) to interactively learn answer-enhanced question representations and path-aware relation representations for relation detection. A Siamese LSTM is employed into a similarity matching process between the question representation and relation representation. Experimental results on the SimpleQuestions and WebQSP datasets demonstrate that KRD outperforms the state-of-the-art methods. In addition, a series of ablation test show the robust superiority of the proposed method.

Community question answering (CQA) gains increasing popularity in both academy and industry recently. However, the redundancy and lengthiness issues of crowdsourced answers limit the performance of answer selection and lead to reading difficulties and misunderstandings for community users. To solve these problems, we tackle the tasks of answer selection and answer summary generation in CQA with a novel joint learning model. Specifically, we design a question-driven pointer-generator network, which exploits the correlation information between question-answer pairs to aid in attending the essential information when generating answer summaries. Meanwhile, we leverage the answer summaries to alleviate noise in original lengthy answers when ranking the relevancy degrees of question-answer pairs. In addition, we construct a new large-scale CQA corpus, WikiHowQA, which contains long answers for answer selection as well as reference summaries for answer summarization. The experimental results show that the joint learning method can effectively address the answer redundancy issue in CQA and achieves state-of-the-art results on both answer selection and text summarization tasks. Furthermore, the proposed model is shown to be of great transferring ability and applicability for resource-poor CQA tasks, which lack of reference answer summaries., Comment: Accepted by AAAI 2020 (oral)

Entropy has become increasingly popular in computer science and information theory because it can be used to measure the predictability and redundancy of knowledge bases, especially ontologies. However, current entropy applications that evaluate ontologies consider only single-point connectivity rather than path connectivity, and they assign equal weights to each entity and path. We propose an Entropy-Aware Path-Based (EAPB) metric for ontology quality by considering the path information between different vertices and textual information included in the path to calculate the connectivity path of the whole network and dynamic weights between different nodes. The information obtained from structure-based embedding and text-based embedding is multiplied by the connectivity matrix of the entropy computation. EAPB is analytically evaluated against the state-of-the-art criteria. We have performed empirical analysis on real-world medical ontologies and a synthetic ontology based on the following three aspects: ontology statistical information (data quantity), entropy evaluation (data quality), and a case study (ontology structure and text visualization). These aspects mutually demonstrate the reliability of the proposed metric. The experimental results show that the proposed EAPB can effectively evaluate ontologies, especially those in the medical informatics field. We leverage path information and textual information to enrich the network representational learning and aid in entropy computation. The analytics and assessments of semantic web can benefit from the structure information but also the text information. We believe that EAPB is helpful for managing ontology development and evaluation projects. Our results are reproducible and we will release the source code and ontology of this work after publication. (Source code and ontology: https://github.com/AnonymousResearcher1/ontologyEvaluate ).

With the rising importance of knowledge exchange, ontologies have become a key technology in the development of shared knowledge models for semantic-driven applications, such as knowledge interchange and semantic integration. Significant progress has been made in the use of entropy to measure the predictability and redundancy of knowledge bases, particularly ontologies. However, the current entropy applications used to evaluate ontologies consider only single-point connectivity rather than path connectivity, assign equal weights to each entity and path, and assume that vertices are static. To address these deficiencies, the present study proposes a Path-based Text-aware Entropy Computation method, PTEC, by considering the path information between different vertices and the textual information within the path to calculate the connectivity path of the whole network and the different weights between various nodes. Information obtained from structure-based embedding and text-based embedding is multiplied by the connectivity matrix of the entropy computation. An experimental evaluation of three real-world ontologies is performed based on ontology statistical information (data quantity), entropy evaluation (data quality), and a case study (ontology structure and text visualization). These aspects mutually demonstrate the reliability of our method. Experimental results demonstrate that PTEC can effectively evaluate ontologies, particularly those in the medical field.