Research on Automatic Terminological Dictionary Extraction Based on Bilingual Parallel Corpus

Abstract

Bilingual dictionaries have always been a basic resource in the fields of machine translation and cross-language information retrieval. The text in parallel corpus is a pair of sentences translated into each other. It is a set of text composed of the source language text and the corresponding translated text, which has strong text alignment characteristics. By making full use of rich corpus information in parallel corpora, a bilingual automatic term extraction system is constructed by designing reasonable algorithms to realize automatic or semi-automatic term extraction, which is used to solve the difficult problems in machine translation and cross-language natural language processing. Based on the method of deep learning, this paper constructs the LSTM model based on RNN. Based on LSTM, a new BLSTM model is formed, which has the advantages of comprehensive information, strong robustness, and the ability to take into account both front and back data in natural language processing, so that the trained machine can learn more abstract samples.