Cross-language article linking with deep neural network based paragraph encoding

Yu-Chun Wang

doi:10.1016/j.csl.2021.101279

Cross-language article linking with deep neural network based paragraph encoding

2022-03-01

1

PRE

AI

Richard Tzong‐Han Tsai *

DOI：10.1016/j.csl.2021.101279

Original

Original request for help

Save

Abstract

En 中文

Cross-language article linking (CLAL), the task of generating links between articles in different languages from different encyclopedias, is critical for facilitating sharing among online knowledge bases. Some previous CLAL research has been done on creating links among Wikipedia wikis, but much of this work depends heavily on simple language patterns and encyclopedia format or metadata. In this paper, we propose a new CLAL method based on deep learning paragraph embeddings to link English Wikipedia articles with articles in Baidu Baike, the most popular online encyclopedia in mainland China. To measure article similarity for link prediction, we employ several neural networks with attention mechanisms, such as CNN and LSTM, to train paragraph encoders that create vector representations of the articles' semantics based only on article text, rather than link structure, as input data. Using our Deep CLALmethod, we compile a data set consisting of Baidu Baike entries and corresponding English Wikipedia entries. Our approach does not rely on linguistic or structural features and can be easily applied to other language pairs by using pre-trained word embeddings, regardless of whether the two languages are on the same encyclopedia platform.

Keywords:

Cross-language article linking

Link discovery

Deep learning

Paragraph encoding

Convolutional neural network

Long short-term memory

Cross-language article linking with deep neural network based paragraph encoding

Abstract

Journal

Organization