Mitigating the Effect of Out-of-Vocabulary Entity Pairs in Matrix Factorization for KB Inference

2018 ◽  
Author(s):  
Prachi Jain ◽  
Shikhar Murty ◽  
Mausam . ◽  
Soumen Chakrabarti
Keyword(s):  
Knowledge Base ◽  
Hybrid Model ◽  
Matrix Factorization ◽  
Relation Extraction ◽  
Tensor Factorization ◽  
Evaluation Protocol

This paper analyzes the varied performance of Matrix Factorization (MF) on the related tasks of relation extraction and knowledge-base completion, which have been unified recently into a single framework of knowledge-base inference (KBI) [Toutanova et al., 2015]. We first propose a new evaluation protocol that makes comparisons between MF and Tensor Factorization (TF) models fair. We find that this results in a steep drop in MF performance. Our analysis attributes this to the high out-of-vocabulary (OOV) rate of entity pairs in test folds of commonly-used datasets. To alleviate this issue, we propose three extensions to MF. Our best model is a TF-augmented MF model. This hybrid model is robust and obtains strong results across various KBI datasets.

scholarly journals An Accelerated Symmetric Nonnegative Matrix Factorization Algorithm Using Extrapolation

Symmetry ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 1187
Author(s):  
Peitao Wang ◽  
Zhaoshui He ◽  
Jun Lu ◽  
Beihai Tan ◽  
YuLei Bai ◽  
...  
Keyword(s):  
Real World ◽  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Nonnegative Matrix ◽  
Low Rank ◽  
Tensor Factorization ◽  
Real World Data ◽  
Restart Strategy ◽  
Extrapolation Scheme ◽  
Symmetric Nonnegative Matrix Factorization

Symmetric nonnegative matrix factorization (SNMF) approximates a symmetric nonnegative matrix by the product of a nonnegative low-rank matrix and its transpose. SNMF has been successfully used in many real-world applications such as clustering. In this paper, we propose an accelerated variant of the multiplicative update (MU) algorithm of He et al. designed to solve the SNMF problem. The accelerated algorithm is derived by using the extrapolation scheme of Nesterov and a restart strategy. The extrapolation scheme plays a leading role in accelerating the MU algorithm of He et al. and the restart strategy ensures that the objective function of SNMF is monotonically decreasing. We apply the accelerated algorithm to clustering problems and symmetric nonnegative tensor factorization (SNTF). The experiment results on both synthetic and real-world data show that it is more than four times faster than the MU algorithm of He et al. and performs favorably compared to recent state-of-the-art algorithms.

scholarly journals Dual CNN for Relation Extraction with Knowledge-Based Attention and Word Embeddings

2019 ◽  
Vol 2019 ◽  
pp. 1-10 ◽  
Author(s):  
Jun Li ◽  
Guimin Huang ◽  
Jianheng Chen ◽  
Yabing Wang
Keyword(s):  
Knowledge Base ◽  
Relation Extraction ◽  
Background Knowledge ◽  
Word Embedding ◽  
Entity Recognition ◽  
Instance Selection ◽  
Attention Model ◽  
Training Tool ◽  
Knowledge Based ◽  
Proposed Model

Relation extraction is the underlying critical task of textual understanding. However, the existing methods currently have defects in instance selection and lack background knowledge for entity recognition. In this paper, we propose a knowledge-based attention model, which can make full use of supervised information from a knowledge base, to select an entity. We also design a method of dual convolutional neural networks (CNNs) considering the word embedding of each word is restricted by using a single training tool. The proposed model combines a CNN with an attention mechanism. The model inserts the word embedding and supervised information from the knowledge base into the CNN, performs convolution and pooling, and combines the knowledge base and CNN in the full connection layer. Based on these processes, the model not only obtains better entity representations but also improves the performance of relation extraction with the help of rich background knowledge. The experimental results demonstrate that the proposed model achieves competitive performance.

scholarly journals Distantly supervised Web relation extraction for knowledge base population

Semantic Web ◽  
2016 ◽  
Vol 7 (4) ◽  
pp. 335-349 ◽  
Author(s):  
Isabelle Augenstein ◽  
Diana Maynard ◽  
Fabio Ciravegna
Keyword(s):  
Knowledge Base ◽  
Relation Extraction ◽  
Base Population ◽  
Knowledge Base Population

Chinese Open Relation Extraction and Knowledge Base Establishment

2018 ◽  
Vol 17 (3) ◽  
pp. 1-22 ◽  
Author(s):  
Shengbin Jia ◽  
Shijia E ◽  
Maozhen Li ◽  
Yang Xiang
Keyword(s):  
Knowledge Base ◽  
Relation Extraction

Power Equipment Technical State Assessment Principles

2014 ◽  
Vol 492 ◽  
pp. 531-535 ◽  
Author(s):  
Stepan A. Dmitriev ◽  
Alexandra I. Khalyasmaa
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuzzy Logic ◽  
Knowledge Base ◽  
Hybrid Model ◽  
State Assessment ◽  
Technical State ◽  
Model Construction ◽  
Power Equipment ◽  
Membership Functions

This article is devoted to the principles of power equipment technical state assessment at 35-220 kV substations. The article deals with the network hybrid model construction using methods of fuzzy logic and artificial neural network. Finally, in order to construct the knowledge base, a methodology of the power equipment technical state assessment, based on the membership functions, is introduced.

NONNEGATIVE TENSOR FACTORIZATION FOR CONTINUOUS EEG CLASSIFICATION

2007 ◽  
Vol 17 (04) ◽  
pp. 305-317 ◽  
Author(s):  
HYEKYOUNG LEE ◽  
YONG-DEOK KIM ◽  
ANDRZEJ CICHOCKI ◽  
SEUNGJIN CHOI
Keyword(s):  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Viterbi Algorithm ◽  
Nonnegative Matrix ◽  
Data Sets ◽  
Tensor Factorization ◽  
Nonnegative Tensor ◽  
Eeg Classification ◽  
Nonnegative Tensor Factorization ◽  
Continuous Eeg

In this paper we present a method for continuous EEG classification, where we employ nonnegative tensor factorization (NTF) to determine discriminative spectral features and use the Viterbi algorithm to continuously classify multiple mental tasks. This is an extension of our previous work on the use of nonnegative matrix factorization (NMF) for EEG classification. Numerical experiments with two data sets in BCI competition, confirm the useful behavior of the method for continuous EEG classification.

Sign in / Sign up

Export Citation Format

Share Document