Show HN: Word2Bits – Quantized Word Vectors

Re:Show HN: Word2Bits – Quantized Word Vectors by newman8r on Tuesday March 20, 2018 @03:19AM (#16626547)

interesting that 'artists' is a furthest neighbor of 'man' in the example

[ Parent | on HN ]

Re:Show HN: Word2Bits – Quantized Word Vectors by maxlam on Tuesday March 20, 2018 @03:22AM (#16626557)

This might be because "Artist" has an uppercase "A" -- I trained all the word vectors to be case sensitive so "Artist" is not the same as "artist" (which should be closer to "man" than "Artist")

[ Parent | on HN ]

Re:Show HN: Word2Bits – Quantized Word Vectors by NKCSS on Tuesday March 20, 2018 @03:26AM (#16626565)

Why would you do that? If you look at something like LSA, they goal is to uniform those, rather than distinguish. artist and Artist should be (near)100% match; what are you trying to do here?

[ Parent | on HN ]

Re:Show HN: Word2Bits – Quantized Word Vectors by maxlam on Tuesday March 20, 2018 @03:29AM (#16626573)

Main reason I did it this way is because Facebook's DrQA (which I evaluate the vectors on for the SQuAD task) uses case sensitive vectors.

Was a tough decision between choosing whether to train case sensitive vectors / case insensitive vectors and a future task would be to train case-insensitive vectors.

[ Parent | on HN ]

Re:Show HN: Word2Bits – Quantized Word Vectors by newman8r on Tuesday March 20, 2018 @03:37AM (#16626596)

Makes sense. The plural vs singular probably impacts that one too.

[ Parent | on HN ]