Exploiting Knowledge Embedding to Improve the Description for Image Captioning

Recently, there has been an upsurge in the number of knowledge graphs (KG) that can only be accessed by experts. Non-expert users lack an adequate understanding of the queried knowledge graph's vocabulary and structure, as well as the syntax of the structured query language used to express the user's information needs. To increase the user base of these KGs, a set of Question Answering (QA) systems that use natural language to query these knowledge graphs have been introduced. However, finding a benchmark that accurately evaluates the quality of a QA system is a difficult task due to (1) the high degree of variation in the fine-grained properties among the existing benchmarks, (2) the static nature of the existing benchmarks versus the evolving nature of KGs, and (3) the limited number of KGs targeted by existing benchmarks, which hinders the usability of QA systems in real-world deployment over KGs that are different from those that were used in the evaluation of the QA systems. In this paper, we introduce Maestro, a benchmark generation system for question answering over knowledge graphs. Maestro can generate a new benchmark for any KG given the KG and, optionally, a text corpus that covers this KG. The benchmark generated by Maestro is guaranteed to cover all the properties of the natural language questions and queries that were encountered in the literature as long as the targeted KG includes these properties. Maestro also generates high-quality natural language questions with various utterances that are on par with manually-generated ones to better evaluate QA systems.

In recent years, medical Question Answering (QA) systems have gained a lot of attentions, since they can not only help professionals make quick decisions, but also give ordinary people advice when they seek for helpful information. However, the interpretability and accuracy problems have plagued QA systems for a long time. In this paper, we propose a QA system, DSQA, based on knowledge graph for answering domain-specific medical questions. The data we use are from Electronic Medical Records (EMRs) that are complex and heterogeneous with varied qualities. We introduce doctor-in-the-loop mechanism to design the knowledge graph, which improves the interpretability and the accuracy of our QA system. For every natural-language question, we generate the answer with a hybrid of the traditional deep learning model and the reasoning on the knowledge graph. Finally, the answer is returned to the user in the format of a subgraph with corresponding natural-language sentences. Our system shows high interpretability and gives excellent performance according to the experiment results.

While RDF was designed to make data easily readable by machines, it does not make data easily usable by end-users. Question Answering (QA) over Knowledge Graphs (KGs) is seen as the technology which is able to bridge this gap. It aims to build systems which are capable of extracting the answer to a user’s natural language question from an RDF dataset.In recent years, many approaches were proposed which tackle the problem of QA over KGs. Despite such efforts, it is hard and cumbersome to create a Question Answering system on top of a new RDF dataset. The main open challenge remains portability, i.e., the possibility to apply a QA algorithm easily on new and previously untested RDF datasets.In this publication, we address the problem of portability by presenting an architecture for a portable QA system. We present a novel approach called QAnswer KG, which allows the construction of on-demand QA systems over new RDF datasets. Hence, our approach addresses non-expert users in QA domain.In this paper, we provide the details of QA system generation process. We show that it is possible to build a QA system over any RDF dataset while requiring minimal investments in terms of training. We run experiments using 3 different datasets.To the best of our knowledge, we are the first to design a process for non-expert users. We enable such users to efficiently create an on-demand, scalable, multilingual, QA system on top of any RDF dataset.

Knowledge graphs (KGs) are widely used in many real-world applications, such as information retrieval, question answering system, and personal recommendation. However, most KGs are suffering from the incompleteness problem. To deal with the task of link prediction, previous knowledge graph embedding methods require numerous reference instances for each relation. It is worth noting that most relations in KGs have only a few reference instances available. Existing works for few-shot link prediction evaluate the authenticity of triplets from a single relation perspective. In this paper, we propose Hybrid Matching Network (HMNet) for few-shot link prediction, evaluating triplets from entity and relation two perspectives. At the entity-aware matching network, HMNet uses attentive inductive embedding layer to aggregate entity features and relation-aware topology, and then provides entity-aware score to implement first perspective evaluation. At the relation-aware matching network, HMNet integrates feature attention mechanism to implement relation perspective evaluation. Experiments on two public datasets indicate that HMNet achieves promising performance in few-shot link prediction.

In recent years, the related research of entity alignment has mainly focused on entity alignment via knowledge embeddings and graph neural networks; however, these proposed models usually suffer from structural heterogeneity and the large-scale problem of knowledge graph. A novel entity alignment model based on graph isomorphic network and compressed sensing is proposed. First, for the problem of structural heterogeneity, graph isomorphic network encoder is applied in knowledge graph to capture structural similarity of entity relation. Second, for the problem of large scale, key node and community are integrated for priority entity alignment to improve execution speed. However, the exiting node importance ranking algorithm cannot accurately identify key node in knowledge graph. So the compressed sensing is adopted in node importance ranking to improve the accuracy of identifying key node. The authors have carried out several experiments to test the effect and efficiency of the proposed entity alignment model.

Given a user question, the goal of a Question Answering (QA) system is to retrieve answers rather than full documents or even best-matching passages, as most Information Retrieval systems currently do. In this paper, we present BRUJA, a QA system for the management of multilingual collections. BRUJ rkstions (English, Spanish and French). The BRUJA architecture is not formed with three monolingual QA systems but instead uses English as Interlingua to make usual QA tasks such as question classifications and answer extractions. In addition, BRUJA uses Cross Language Information Retrieval (CLIR) techniques to retrieve relevant documents from a multilingual collection. On the one hand, we have more documents to find answers from but on the other hand, we are introducing noise into the system because of translations to the Interlingua (English) and the CLIR module. The question is whether the difficulty of managing three languages is worth it or whether a monolingual QA system delivers better results. We report on in-depth experimentation and demonstrate that our multilingual QA system gets better results than its monolingual counterpart whenever it uses good translation resources and, especially, CLIR techniques that are state-of-the-art.

An authoring tool for decision support systems in context questions of ecological knowledge

The prosperous development of cognition and human-level intelligence have made the creation of large-scale domain knowledge graphs (KGs) a hot research field. Entity alignment (EA), which discovers entity pairs that represent the same real object in different KGs, is the key technology for building large scale knowledge graph. Existing EA methods rely mainly on the vector representation of the entity and ignoring the semantic features of an entity in a KG, result in poor alignment quality. To address this limitation, we propose a new EA framework based on knowledge embeddings (KEs) and type matching constraints. By embedding two KGs into a unified vector space, we combine the similarity of the entity vector and the degree of the entity type matching to perform more accurate cross-KG EA. The experimental results show that our proposed method has very good performance on both cross-KG and cross-language data sets. On the DBP-YG dataset, in terms of Hit@1, Hits@10, and MRR, our methods have an average increase of 27% over the baseline method MTransE. In most cases, our method significantly improves the accuracy of EA compared with state-of-the-art methods.

Advances in machine learning and deep learning methods, together with the increasing availability of large-scale pharmacological, genomic, and chemical datasets, have created opportunities for identifying potentially useful relationships within biochemical networks. Knowledge embedding models have been found to have value in detecting knowledge-based correlations among entities, but little effort has been made to apply them to networks of biochemical entities. This is because such networks tend to be unbalanced and sparse, and knowledge embedding models do not work well on them. However, to some extent, the shortcomings of knowledge embedding models can be compensated for if they are used in association with graph embedding. In this paper, we combine knowledge embedding and graph embedding to represent biochemical entities and their relations as dense and low-dimensional vectors. We build a cascade learning framework which incorporates semantic features from the knowledge embedding model, and graph features from the graph embedding model, to score the probability of linking. The proposed method performs noticeably better than the models with which it is compared. It predicted links and entities with an accuracy of 93%, and its average hits@10 score has an average of 8.6% absolute improvement compared with original knowledge embedding model, 1.1% to 9.7% absolute improvement compared with other knowledge and graph embedding algorithm. In addition, we designed a meta-path algorithm to detect path relations in the biomedical network. Case studies further verify the value of the proposed model in finding potential relationships between diseases, drugs, genes, treatments, etc. Amongst the findings of the proposed model are the suggestion that VDR (vitamin D receptor) may be linked to prostate cancer. This is backed by evidence from medical databases and published research, supporting the suggestion that our proposed model could be of value to biomedical researchers.

Question Answering (QA) systems are becoming the inspiring model for the future of search engines. While, recently, datasets underlying QA systems have been promoted from unstructured datasets to structured datasets with semantically highly enriched metadata, question answering systems are still facing serious challenges and are therefore not meeting users' expectations. This paper provides an exhaustive insight of challenges known so far for building QA systems, with a special focus on employing structured data (i.e. knowledge graphs).It thus helps researchers to easily spot gaps to fill with their future research agendas.

Iterative rule-guided reasoning over sparse knowledge graphs with deep reinforcement learning

To meet the high-efficiency question answering needs of existing patients and doctors, this system integrates medical professional knowledge, knowledge graphs, and question answering systems that conduct man-machine dialogue through natural language. This system locates the medical field, uses crawler technology to use vertical medical websites as data sources, and uses diseases as the core entity to construct a knowledge graph containing 44,000 knowledge entities of 7 types and 300,000 entities of 11 kinds. It is stored in the Neo4j graph database, using rule-based matching methods and string-matching algorithms to construct a domain lexicon to classify and query questions. This system has specific practical value in the medical field knowledge graph and question answering system.

Knowledge Graphs (KGs) have shown to be very important for applications such\nas personal assistants, question-answering systems, and search engines.\nTherefore, it is crucial to ensure their high quality. However, KGs inevitably\ncontain errors, duplicates, and missing values, which may hinder their adoption\nand utility in business applications, as they are not curated, e.g.,\nlow-quality KGs produce low-quality applications that are built on top of them.\nIn this vision paper, we propose a practical knowledge graph curation framework\nfor improving the quality of KGs. First, we define a set of quality metrics for\nassessing the status of KGs, Second, we describe the verification and\nvalidation of KGs as cleaning tasks, Third, we present duplicate detection and\nknowledge fusion strategies for enriching KGs. Furthermore, we give insights\nand directions toward a better architecture for curating KGs.\n

With the change of health concept and medical model, traditional Chinese medicine (TCM) has shown more and more unique advantages. Users expect to query TCM knowledge efficiently through online. At the same time, intelligent question-answering system based on knowledge graphs is gradually becoming a new trend of natural interaction between humans and machines. It uses knowledge graph as the source of answers, which can more accurately understand the user’s questions described in natural language, and return more precise answers according to the real intention of the user. This paper extracts the triples of TCM knowledge from the instructions of pharmacy database and the special database of TCM and then stores them in the Neo4j graph database. Based on this knowledge graph, the question-answering system of TCM is realized. For the natural sentences entered by users, the question-answering system first identifies the entities in the sentences, then combines TF-IDF and word vector to generate sentence vectors, matches the most similar question-answering template, searches the answers in the knowledge graph according to the semantics of the templates and the entities in the questions, and finally answers the questions according to the returned data. The system can accurately answer the main components and pharmaceutical enterprises of TCM, which diseases and symptoms can be treated by TCM and so on.

An implicit aspect-based sentiment analysis method using supervised contrastive learning and knowledge embedding