Sentiment Analysis and Basic Feature Extraction (Natural Language Processing at UT Austin)

Part of a series of video lectures for CS388: Natural Language Processing, a masters-level NLP course offered as part of the Masters of Computer Science Online at UT Austin. For accompanying readings, see www.cs.utexas....

[@javidjamae]

How do you generally handle misspelled words in pre-processing? Do you rewrite them as corrected words or treat them as UNK?

[@javidjamae]

Can you please explain how adding an extra feature to the feature vector the equivalent of having a entire bias vector? Correct me if I’m wrong, but a bias vector would contain biases for each feature (or node in a NN layer), whereas adding a bias as a single new feature would be a single bias alongside all the features so could only have an aggregate effect. It seems like these are not equivalent and would have dimensionally different impact/results.

[@aureas8373]

correct me if i'm wrong, but i think the b bias itself was supposed to be appended to the w vector (as 1 was appended to the f(x) vector) which would then be equivalent to the + b in the original expression.