# Differences

This shows you the differences between two versions of the page.

 courses:rg:2014:wr [2014/11/04 01:24]hoangt created courses:rg:2014:wr [2014/11/04 14:41] (current)popel 2014/11/04 14:41 popel 2014/11/04 01:26 hoangt 2014/11/04 01:24 hoangt 2014/11/04 01:24 hoangt 2014/11/04 01:24 hoangt created Next revision Previous revision 2014/11/04 14:41 popel 2014/11/04 01:26 hoangt 2014/11/04 01:24 hoangt 2014/11/04 01:24 hoangt 2014/11/04 01:24 hoangt created Line 2: Line 2: 1. In three main types of word representations described in the paper, to which types the following two samples belong: 1. In three main types of word representations described in the paper, to which types the following two samples belong: - a) dog -0.087099201783 -0.136966257697 0.106813367913 [47 more numbers] + a) + dog -0.087099201783 -0.136966257697 0.106813367913 [47 more numbers] cat -0.103287428163 -0.0066971301398 -0.0346911076188 [47 more numbers] cat -0.103287428163 -0.0066971301398 -0.0346911076188 [47 more numbers] - b) dog 11010111010 + b) + dog 11010111010 cat 11010111010 cat 11010111010 - + 2. Section 4.1 defines a corrupted (or noise) n-gram, but there is a tiny error/typo in the definition. Try nitpicking and point it out. - 2. Section 4.1 defines a corrupted (or noise) n-gram, but there is a tiny error/typo in the definition. Try to be nitpicking and point it out. + 3. Section 7.4 states that "word representations in NER brought larger gains on the out-of-domain data than on the in-domain data." Try to guess what is the reason. 3. Section 7.4 states that "word representations in NER brought larger gains on the out-of-domain data than on the in-domain data." Try to guess what is the reason. Line 15: Line 16: b) Does it contain any compound feature with word representations?​ b) Does it contain any compound feature with word representations?​ c) Give an example of a possible compound feature with word representations for the NER task. c) Give an example of a possible compound feature with word representations for the NER task. + + 5. + Consider the C&W embedding vectors with 50 dimensions. Guess which word has the embedding vector most similar (by Euclidean distance) to the following vector: + a) vector(king) - vector(man) + vector(woman) + b) vector(dollars) - vector(dollar) + vector(mouse) **Hint** : The paper is 11-page long. You can skip section 2 and section 3.2 which are the literature review. **Hint** : The paper is 11-page long. You can skip section 2 and section 3.2 which are the literature review.

[ Back to the navigation ] [ Back to the content ]