دانشگاه سمنان

 آمار

تعداد نشریات21
تعداد شماره‌ها610
تعداد مقالات9,027
تعداد مشاهده مقاله67,082,791
تعداد دریافت فایل اصل مقاله7,656,234
Abdolahi, Mohamad, Zahedi, Morteza. (1398). A New Method for Sentence Vector Normalization Using Word2vec. نشریه هنرهای کاربردی, 10(2), 87-96. doi: 10.22075/ijnaa.2019.4177
Mohamad Abdolahi; Morteza Zahedi. "A New Method for Sentence Vector Normalization Using Word2vec". نشریه هنرهای کاربردی, 10, 2, 1398, 87-96. doi: 10.22075/ijnaa.2019.4177
Abdolahi, Mohamad, Zahedi, Morteza. (1398). 'A New Method for Sentence Vector Normalization Using Word2vec', نشریه هنرهای کاربردی, 10(2), pp. 87-96. doi: 10.22075/ijnaa.2019.4177
Abdolahi, Mohamad, Zahedi, Morteza. A New Method for Sentence Vector Normalization Using Word2vec. نشریه هنرهای کاربردی, 1398; 10(2): 87-96. doi: 10.22075/ijnaa.2019.4177

A New Method for Sentence Vector Normalization Using Word2vec

International Journal of Nonlinear Analysis and Applications
مقاله 39، دوره 10، شماره 2، اسفند 2019، صفحه 87-96    اصل مقاله (355.95 K)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22075/ijnaa.2019.4177
نویسندگان
Mohamad Abdolahi* ؛ Morteza Zahedi
Kharazmi International Campus Shahrood University of Technology, Shahrood, Iran
تاریخ دریافت: 11 دی 1398،  تاریخ پذیرش: 11 دی 1398 
چکیده
Word embeddings (WE) have received much attention recently as word to numeric vectors architecture for all text processing approaches and has been a great asset for a large variety of NLP tasks. Most of text processing task tried to convert text components like sentences to numeric matrix to apply their processing algorithms. But the most important problems in all word vector-based text processing approaches are different sentences size and as a result, different dimension of sentences matrices. In this paper, we suggest an efficient but simple statistical method to convert text sentences into equal dimension and normalized matrices Proposed method aims to combines three most efficient methods (averaging based, most likely n-grams, and word’s mover distance) to use their advantages and reduce their constraints. The unique size resulting matrix does not depend on language, Subject and scope of the text and words semantic concepts. Our results demonstrate that normalized matrices capture complementary aspects of most text processing tasks such as coherence evaluation, text summarization, text classification, automatic essay scoring, and question answering.
کلیدواژه‌ها
Text Preprocessing؛ Sentence Normalization؛ Word Embedding؛ Word Vector؛ Sentence Vector
آمار
تعداد مشاهده مقاله: 15,472
تعداد دریافت فایل اصل مقاله: 1,217


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب