标签:NLP vectors Word matrix each WR words Representation word
【刘知远NLP课 整理】Word Representation
Word representation is a process that transform the symbols to the machine understandable meanings. The goals of Word Representation are
- Compute word similarity
WR(Star) ≃ WR(Sun)
WR(Motel) ≃ WR(Hotel)
- Infer word relation
WR(China) − WR(Beijing) ≃ WR(Japan) - WR(Tokyo)
WR(Man) ≃ WR(King) − WR(Queen) + WR(Woman)
WR(Swimming) ≃ WR(Walking) − WR(Walk) + WR(Swim)
Now we start to discuss some ways of obtaining word representations.
1. Use a set of related words
Such as using synonyms and hypernyms to represent a word. e.g. WordNet, a resource containing synonym and hypernym sets.
However, lots of problems exist:
-
Missing nuance
("proficient", "good") are synonyms only in some contexts
-
Missing new meanings of words
Apple (fruit → IT company)
-
Subjective
-
Data sparsity
-
Requires human labor to create and adapt
2. One-Hot Representation
Regard words as discrete symbols.
- Vector dimension = # words in vocabulary
- Token with greater ID value doesn't imply more or less important as compared with the token with less ID value.
The problem is all the vectors are orthogonal. No natural notion of similarity for one-hot vectors.
\[标签:NLP,vectors,Word,matrix,each,WR,words,Representation,word 来源: https://www.cnblogs.com/thousfeet/p/15144001.html
本站声明: 1. iCode9 技术分享网(下文简称本站)提供的所有内容,仅供技术学习、探讨和分享; 2. 关于本站的所有留言、评论、转载及引用,纯属内容发起人的个人观点,与本站观点和立场无关; 3. 关于本站的所有言论和文字,纯属内容发起人的个人观点,与本站观点和立场无关; 4. 本站文章均是网友提供,不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属;如您发现该文章侵犯了您的权益,可联系我们第一时间进行删除; 5. 本站为非盈利性的个人网站,所有内容不会用来进行牟利,也不会利用任何形式的广告来间接获益,纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。