scholarly journals A Knowledge Base Completion Model Based on Path Feature Learning

2018 ◽  
Vol 13 (1) ◽  
pp. 71 ◽  
Author(s):  
Xixun Lin ◽  
Yanchun Liang ◽  
Limin Wang ◽  
Xu Wang ◽  
Mary Qu Yang ◽  
...  
Keyword(s):  
Knowledge Base ◽  
Large Scale ◽  
Relational Learning ◽  
Feature Learning ◽  
Statistical Relational Learning ◽  
Knowledge Bases ◽  
Ranking Algorithm ◽  
Stage Model ◽  
Second Stage ◽  
Urgent Task

Large-scale knowledge bases, as the foundations for promoting the development of artificial intelligence, have attracted increasing attention in recent years. These knowledge bases contain billions of facts in triple format; yet, they suffer from sparse relations between entities. Researchers proposed the path ranking algorithm (PRA) to solve this fatal problem. To improve the scalability of knowledge inference, PRA exploits random walks to find Horn clauses with chain structures to predict new relations given existing facts. This method can be regarded as a statistical classification issue for statistical relational learning (SRL). However, large-scale knowledge base completion demands superior accuracy and scalability. In this paper, we propose the path feature learning model (PFLM) to achieve this urgent task. More precisely, we define a two-stage model: the first stage aims to learn path features from the existing knowledge base and extra parsed corpus; the second stage uses these path features to predict new relations. The experimental results demonstrate that the PFLM can learn meaningful features and can achieve significant and consistent improvements compared with previous work.

scholarly journals Using Semantics and Statistics to Turn Data into Knowledge

AI Magazine ◽  
2015 ◽  
Vol 36 (1) ◽  
pp. 65-74 ◽  
Author(s):  
Jay Pujara ◽  
Hui Miao ◽  
Lise Getoor ◽  
William W. Cohen
Keyword(s):  
Knowledge Base ◽  
State Of The Art ◽  
Relational Learning ◽  
Statistical Relational Learning ◽  
Knowledge Bases ◽  
Knowledge Graph ◽  
Learning Framework ◽  
Knowledge Base Construction ◽  
Order Of Magnitude ◽  
Soft Logic

Many information extraction and knowledge base construction systems are addressing the challenge of deriving knowledge from text. A key problem in constructing these knowledge bases from sources like the web is overcoming the erroneous and incomplete information found in millions of candidate extractions. To solve this problem, we turn to semantics — using ontological constraints between candidate facts to eliminate errors. In this article, we represent the desired knowledge base as a knowledge graph and introduce the problem of knowledge graph identification, collectively resolving the entities, labels, and relations present in the knowledge graph. Knowledge graph identification requires reasoning jointly over millions of extractions simultaneously, posing a scalability challenge to many approaches. We use probabilistic soft logic (PSL), a recently-introduced statistical relational learning framework, to implement an efficient solution to knowledge graph identification and present state-of-the-art results for knowledge graph construction while performing an order of magnitude faster than competing methods.

scholarly journals Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base

2020 ◽  
Author(s):  
Yongrui Chen ◽  
Huiying Li ◽  
Yuncheng Hua ◽  
Guilin Qi
Keyword(s):  
Knowledge Base ◽  
Structure Prediction ◽  
Question Answering ◽  
State Transition ◽  
Knowledge Bases ◽  
Second Stage ◽  
Transition Strategy ◽  
Query Structure ◽  
Two Stages ◽  
Complex Question

Formal query building is an important part of complex question answering over knowledge bases. It aims to build correct executable queries for questions. Recent methods try to rank candidate queries generated by a state-transition strategy. However, this candidate generation strategy ignores the structure of queries, resulting in a considerable number of noisy queries. In this paper, we propose a new formal query building approach that consists of two stages. In the first stage, we predict the query structure of the question and leverage the structure to constrain the generation of the candidate queries. We propose a novel graph generation framework to handle the structure prediction task and design an encoder-decoder model to predict the argument of the predetermined operation in each generative step. In the second stage, we follow the previous methods to rank the candidate queries. The experimental results show that our formal query building approach outperforms existing methods on complex questions while staying competitive on simple questions.

COMBINING DEFAULT LOGIC DATABASES

1994 ◽  
Vol 03 (03) ◽  
pp. 319-348 ◽  
Author(s):  
CHITTA BARAL ◽  
SARIT KRAUS ◽  
JACK MINKER ◽  
V. S. SUBRAHMANIAN
Keyword(s):  
Knowledge Representation ◽  
Knowledge Base ◽  
Large Scale ◽  
Future Generation ◽  
Knowledge Bases ◽  
Default Logic ◽  
Integrity Constraints ◽  
Specialized Knowledge ◽  
The Past ◽  
The Future

During the past decade, it has become increasingly clear that the future generation of large-scale knowledge bases will consist, not of one single isolated knowledge base, but a multiplicity of specialized knowledge bases that contain knowledge about different domains of expertise. These knowledge bases will work cooperatively, pooling together their varied bodies of knowledge, so as to be able to solve complex problems that no single knowledge base, by itself, would have been able to address successfully. In any such situation, inconsistencies are bound to arise. In this paper, we address the question: "Suppose we have a set of knowledge bases, KB1, …, KBn, each of which uses default logic as the formalism for knowledge representation, and a set of integrity constraints IC. What knowledge base constitutes an acceptable combination of KB1, …, KBn?"

scholarly journals A Fast Learning Method for Accurate and Robust Lane Detection Using Two-Stage Feature Extraction with YOLO v3

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4308 ◽  
Author(s):  
Xiang Zhang ◽  
Wei Yang ◽  
Xiaolin Tang ◽  
Jie Liu
Keyword(s):  
Learning Algorithm ◽  
Structural Parameters ◽  
Feature Learning ◽  
Automatic Generation ◽  
Detection Algorithm ◽  
Lane Detection ◽  
Stage Model ◽  
Two Stage ◽  
Label Data ◽  
Second Stage

To improve the accuracy of lane detection in complex scenarios, an adaptive lane feature learning algorithm which can automatically learn the features of a lane in various scenarios is proposed. First, a two-stage learning network based on the YOLO v3 (You Only Look Once, v3) is constructed. The structural parameters of the YOLO v3 algorithm are modified to make it more suitable for lane detection. To improve the training efficiency, a method for automatic generation of the lane label images in a simple scenario, which provides label data for the training of the first-stage network, is proposed. Then, an adaptive edge detection algorithm based on the Canny operator is used to relocate the lane detected by the first-stage model. Furthermore, the unrecognized lanes are shielded to avoid interference in subsequent model training. Then, the images processed by the above method are used as label data for the training of the second-stage model. The experiment was carried out on the KITTI and Caltech datasets, and the results showed that the accuracy and speed of the second-stage model reached a high level.

scholarly journals Intellectualization of Emergency Control of Power Systems on the Basis of Incorporated Ontologies of Knowledge-Bases

2019 ◽  
Vol 13 (2) ◽  
pp. 86-94
Author(s):  
Vladimir Morkun ◽  
Ihor Kotov
Keyword(s):  
Decision Support ◽  
Decision Support System ◽  
Power Systems ◽  
Power System ◽  
Knowledge Base ◽  
Support System ◽  
Large Scale ◽  
Knowledge Bases ◽  
Experiment Planning ◽  
Control Actions

Abstract The research deals with improvement of methods and systems of controlling integrated power systems (IPSs) on the basis of intellectualization of decision-making support. Complex analysis of large-scale accidents at power facilities is performed, and their causes and damages are determined. There is substantiated topicality of building condition knowledge-bases as the foundation for developing decision-support systems in power engineering. The top priorities of the research include developing methods of building a knowledge base based on intensity models of control actions influencing the parameters of power system conditions and introducing the smart system into information contours of the automated dispatch control system (ADCS), as well as assessing practical results of the research. To achieve these goals, the authors apply methods of experiment planning, artificial intelligence, knowledge presentation, mathematical simulation, and mathematical statistics as well as methods of power systems studying. The basic research results include regression models of a power system sensitivity to control actions, methods of building a knowledge base based on the models of sensitivity matrices, a structure of the smart decision-support system, a scheme of introducing the decision-support system into the operating ADCS environment. The problem of building a knowledge base of the dispatch decision-support system on the basis of empirical data resulted from calculating experiments on the system diagram has been solved. The research specifies practical efficiency of the suggested approaches and developed models.

scholarly journals Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning

2020 ◽  
Author(s):  
Yuncheng Hua ◽  
Yuan-Fang Li ◽  
Gholamreza Haffari ◽  
Guilin Qi ◽  
Wei Wu
Keyword(s):  
Knowledge Base ◽  
Large Scale ◽  
Question Answering ◽  
Knowledge Bases ◽  
Retrieval Model ◽  
Test Question ◽  
Weak Supervision ◽  
Meta Learning ◽  
Complex Knowledge ◽  
Complex Question

A compelling approach to complex question answering is to convert the question to a sequence of actions, which can then be executed on the knowledge base to yield the answer, aka the programmer-interpreter approach. Use similar training questions to the test question, meta-learning enables the programmer to adapt to unseen questions to tackle potential distributional biases quickly. However, this comes at the cost of manually labeling similar questions to learn a retrieval model, which is tedious and expensive. In this paper, we present a novel method that automatically learns a retrieval model alternately with the programmer from weak supervision, i.e., the system’s performance with respect to the produced answers. To the best of our knowledge, this is the first attempt to train the retrieval model with the programmer jointly. Our system leads to state-of-the-art performance on a large-scale task for complex question answering over knowledge bases. We have released our code at https://github.com/DevinJake/MARL.

scholarly journals Tandem Inference: An Out-of-Core Streaming Algorithm for Very Large-Scale Relational Inference

2020 ◽  
Vol 34 (06) ◽  
pp. 10259-10266
Author(s):  
Sriram Srinivasan ◽  
Eriq Augustine ◽  
Lise Getoor
Keyword(s):  
Graphical Models ◽  
Large Scale ◽  
Relational Learning ◽  
Statistical Relational Learning ◽  
Rule Based ◽  
Novel Technique ◽  
Gradient Based ◽  
Streaming Algorithm ◽  
Soft Logic ◽  
Machine Memory

Statistical relational learning (SRL) frameworks allow users to create large, complex graphical models using a compact, rule-based representation. However, these models can quickly become prohibitively large and not fit into machine memory. In this work we address this issue by introducing a novel technique called tandem inference (ti). The primary idea of ti is to combine grounding and inference such that both processes happen in tandem. ti uses an out-of-core streaming approach to overcome memory limitations. Even when memory is not an issue, we show that our proposed approach is able to do inference faster while using less memory than existing approaches. To show the effectiveness of ti, we use a popular SRL framework called Probabilistic Soft Logic (PSL). We implement ti for PSL by proposing a gradient-based inference engine and a streaming approach to grounding. We show that we are able to run an SRL model with over 1B cliques in under nine hours and using only 10 GB of RAM; previous approaches required more than 800 GB for this model and are infeasible on common hardware. To the best of our knowledge, this is the largest SRL model ever run.

scholarly journals Error Detection in a Large-Scale Lexical Taxonomy

Information ◽  
2020 ◽  
Vol 11 (2) ◽  
pp. 97 ◽  
Author(s):  
Yinan An ◽  
Sifan Liu ◽  
Hongzhi Wang
Keyword(s):  
Artificial Intelligence ◽  
Knowledge Base ◽  
Error Detection ◽  
Large Scale ◽  
Knowledge Bases ◽  
Experimental Results ◽  
Knowledge Graph ◽  
Significant Challenge

Knowledge base (KB) is an important aspect in artificial intelligence. One significant challenge faced by KB construction is that it contains many noises, which prevent its effective usage. Even though some KB cleansing algorithms have been proposed, they focus on the structure of the knowledge graph and neglect the relation between the concepts, which could be helpful to discover wrong relations in KB. Motived by this, we measure the relation of two concepts by the distance between their corresponding instances and detect errors within the intersection of the conflicting concept sets. For efficient and effective knowledge base cleansing, we first apply a distance-based model to determine the conflicting concept sets using two different methods. Then, we propose and analyze several algorithms on how to detect and repair the errors based on our model, where we use a hash method for an efficient way to calculate distance. Experimental results demonstrate that the proposed approaches could cleanse the knowledge bases efficiently and effectively.

scholarly journals Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation

Algorithms ◽  
2018 ◽  
Vol 11 (9) ◽  
pp. 137 ◽  
Author(s):  
Qingyao Ai ◽  
Vahid Azizi ◽  
Xu Chen ◽  
Yongfeng Zhang
Keyword(s):  
Knowledge Base ◽  
Collaborative Filtering ◽  
Large Scale ◽  
Explicit Knowledge ◽  
State Of The Art ◽  
Representation Learning ◽  
Knowledge Bases ◽  
Personalized Recommendation ◽  
Structured Knowledge ◽  
Explainable Recommendation

Providing model-generated explanations in recommender systems is important to user experience. State-of-the-art recommendation algorithms—especially the collaborative filtering (CF)- based approaches with shallow or deep models—usually work with various unstructured information sources for recommendation, such as textual reviews, visual images, and various implicit or explicit feedbacks. Though structured knowledge bases were considered in content-based approaches, they have been largely ignored recently due to the availability of vast amounts of data and the learning power of many complex models. However, structured knowledge bases exhibit unique advantages in personalized recommendation systems. When the explicit knowledge about users and items is considered for recommendation, the system could provide highly customized recommendations based on users’ historical behaviors and the knowledge is helpful for providing informed explanations regarding the recommended items. A great challenge for using knowledge bases for recommendation is how to integrate large-scale structured and unstructured data, while taking advantage of collaborative filtering for highly accurate performance. Recent achievements in knowledge-base embedding (KBE) sheds light on this problem, which makes it possible to learn user and item representations while preserving the structure of their relationship with external knowledge for explanation. In this work, we propose to explain knowledge-base embeddings for explainable recommendation. Specifically, we propose a knowledge-base representation learning framework to embed heterogeneous entities for recommendation, and based on the embedded knowledge base, a soft matching algorithm is proposed to generate personalized explanations for the recommended items. Experimental results on real-world e-commerce datasets verified the superior recommendation performance and the explainability power of our approach compared with state-of-the-art baselines.

scholarly journals A Comparative Study of Distributional and Symbolic Paradigms for Relational Learning

2019 ◽  
Author(s):  
Sebastijan Dumancic ◽  
Alberto Garcia-Duran ◽  
Mathias Niepert
Keyword(s):  
Euclidean Space ◽  
Knowledge Base ◽  
Relational Learning ◽  
Statistical Relational Learning ◽  
Representation Learning ◽  
The Other ◽  
Learning Approaches ◽  
Relational Knowledge ◽  
Knowledge Graphs ◽  
Relational Classification

Many real-world domains can be expressed as graphs and, more generally, as multi-relational knowledge graphs. Though reasoning and learning with knowledge graphs has traditionally been addressed by symbolic approaches such as Statistical relational learning, recent methods in (deep) representation learning have shown promising results for specialised tasks such as knowledge base completion. These approaches, also known as distributional, abandon the traditional symbolic paradigm by replacing symbols with vectors in Euclidean space. With few exceptions, symbolic and distributional approaches are explored in different communities and little is known about their respective strengths and weaknesses. In this work, we compare distributional and symbolic relational learning approaches on various standard relational classification and knowledge base completion tasks. Furthermore, we analyse the properties of the datasets and relate them to the performance of the methods in the comparison. The results reveal possible indicators that could help in choosing one approach over the other for particular knowledge graphs.

Sign in / Sign up

Export Citation Format

Share Document