Learning to Represent Words by how They’re Spelled

19 מרץ, 2018 ב- 23:02 | פורסם בEnglish, חישובית, כתיב | כתיבת תגובה


A fundamental question in Natural Language Processing (NLP) is how to represent words. If we have a paragraph we want to translate, or a product review we want to determine whether is positive or negative, or a question we want to answer, ultimately the easiest building block to start from is the individual word. The main problem of this approach is that treating each word as just a symbol loses a lot of information. How can we tell from such a representation that the relationship between the symbol PAGE and the symbol PAPER is not the same as that between PAGE and MOON?

Some popular techniques exist that try to learn an abstract representation which identifies these relationships and preserves them. In essence, what these methods do is go over a huge body of text (a corpus), like the entire English Wikipedia, word by word, and come up…

View original post 518 מילים נוספות

מודעות פרסומת

בלוג בוורדפרס.קום.
Entries וכן תגובות feeds.