Bayesian Non-Exhaustive Classification A Case Study

Abstract

The name entity disambiguation task aims to partition the records of multiple real-life persons so that each partition contains records pertaining to a unique person. Most of the existing solutions for this task operate in a batch mode, where all records to be disambiguated are initially available to the algorithm. However, more realistic settings require that the name disambiguation task be performed in an online fashion, in addition to, being able to identify records of new ambiguous entities having no preexisting records. In this work, we propose a Bayesian non-exhaustive classification framework for solving online name disambiguation task. Our proposed method uses a Dirichlet process prior with a Normal × Normal × Inverse Wishart data model which enables identification of new ambiguous entities who have no records in the training data. For online classification, we use one sweep Gibbs sampler which is very efficient and effective. As a case study we consider bibliographic data in a temporal stream format and disambiguate authors by partitioning their papers into homogeneous groups. Our experimental results demonstrate that the proposed method is better than existing methods for performing online name disambiguation task.

High‐degree penalty based global statistical network embedding for name disambiguation in anonymized graph

“…Name disambiguation, also known as name recognition, 16 entity resolution, 17 web appearance disambiguation, 18 and object differentiation, 19 has been extensively studied by different communities for decades. The proposed methods for name disambiguation can be generally categorized as supervised, [20][21][22][23][24] unsupervised. [25][26][27][28] In the supervised scenario, Han et al 20 used support vector machine and Naive Bayes to predict the categorical relationships between author names and entities.…”

Whois? Deep Author Name Disambiguation Using Bibliographic Data

“…Supervised approaches [7,10,11,25,26] are also widely used but mainly only after applying to block that gathers authors sharing the same names together. Han et al [10] present two supervised learning approaches to disambiguate authors in cited references.…”

“…It uses a combination of bi-directional recurrent neural networks (BRNN) along with Long Short Term Memory (LSTM) as the hidden units to generate a distributed representation for each tuple to capture the similarities between them. Zhang et al [7] proposed an online Bayesian approach to identify authors with ambiguous names and as a case study, bibliographic data in a temporal stream format is used and the disambiguation is resolved by partitioning the papers into homogeneous groups.…”

“…Since these problems are known for decades, several studies [1][2][3][4][5][6][7][8][9] have been conducted using different machine learning approaches. This problem is often tackled using supervised approaches such as Support Vector Machine (SVM) [10], Bayesian Classification [7] and Neural networks (NN) [11]. These approaches rely on the matching between publications and authors which are verified either manually or automatically.…”