A resource-light method for cross-lingual semantic textual similarity
TL
TL;DR
An unsupervised and a very resource-light approach for measuring semantic similarity between texts in different languages, applicable to virtually any pair of languages for which there exists a sufficiently large corpus, required to learn monolingual word embeddings.
References52 items
1
Learning bilingual word embeddings with (almost) no bilingual data
2
Interpretable semantic textual similarity: Finding and explaining differences between sentences
3
Cross-language plagiarism detection over continuous-space- and knowledge graph-based representations of language
4
A systematic study of knowledge graph analysis for cross-language plagiarism detection
5