Tibetan Sentence Similarity Evaluation Based on Vectorized Representation Techniques

Autor:	Cai Rangjia, Cizhen Jiacuo, Zhou Maoxian
Rok vydání:	2020
Předmět:	Jaccard index Word embedding business.industry Computer science computer.software_genre Euclidean distance Sentence similarity Subject (grammar) Related research Artificial intelligence Representation (mathematics) business computer Natural language processing
Zdroj:	Lecture Notes in Computer Science ISBN: 9783030381882 CLSW
DOI:	10.1007/978-3-030-38189-9_48
Popis:	Sentence similarity evaluation is an essential subject among the researching fields of Natural Language Processing (NLP), however, Tibetan related research on this subject is fairly inactive and has rarely drawn attention. In this work, we proposed an approach by leveraging vectorized representation techniques to tackle this problem by implementing two methods, namely, Euclidean distance evaluation and Jaccard similarity evaluation. Experiments indicated the performance of presented methods is satisfactory.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::1c2d2fdbfb81fde449b032bfdc550ad9 https://doi.org/10.1007/978-3-030-38189-9_48 Zobrazit plný text záznamu