A cross-lingual sentence pair interaction feature capture model based on pseudo-corpus and multilingual embedding

Abstract

Recently, the emergence of the digital language division and the availability of cross-lingual benchmarks make researches of cross-lingual texts more popular. However, the performance of existing methods based on mapping relation are not good enough, because sometimes the structures of language spaces are not isomorphic. Besides, polysemy makes the extraction of interaction features hard. For cross-lingual word embedding, a model named Cross-lingual Word Embedding Space Based on Pseudo Corpus (CWE-PC) is proposed to obtain cross-lingual and multilingual word embedding. For cross-lingual sentence pair interaction feature capture, a Cross-language Feature Capture Based on Similarity Matrix (CFC-SM) model is built to extract cross-lingual interaction features. ELMo pretrained model and multiple layer convolution are used to alleviate polysemy and extract interaction features. These models are evaluated on multiple language pairs and results show that they outperform the state-of-the-art cross-lingual word embedding methods.

Optimization Strategies and Efficacy Evaluation of Cross-Language Embedding Model in Teaching English in Colleges and Universities

“…Cross-language embedding model is a powerful tool to encode texts from different languages into a shared embedding space [1][2], which enables it to be applied to a series of downstream tasks, such as text classification, text clustering, etc. It also utilizes semantic information to understand the language, which solves the impact of ambiguity on the accuracy of cross-language text classification [3][4][5].…”