Deep learning with text: Learning when to skim and when to read
1–10 of 22 posts
Re: Deep learning with text: Learning when to skim and when to read
#2So... We are now automating laziness? There goes my last stronghold...
Re: Deep learning with text: Learning when to skim and when to read
#3So... We are now automating laziness? There goes my last stronghold...
Isn't automation "laziness incarnate"?
Re: Deep learning with text: Learning when to skim and when to read
#4Re: Deep learning with text: Learning when to skim and when to read
#5Re: Deep learning with text: Learning when to skim and when to read
#6So... We are now automating laziness? There goes my last stronghold...
Not quiet! Choosing between using a fast mostly accurate model and a slow very accurate model. Time saved vs accuracy gained.
Re: Deep learning with text: Learning when to skim and when to read
#7So... We are now automating laziness? There goes my last stronghold...
Skimmming is definitely not a bad thing.
Re: Deep learning with text: Learning when to skim and when to read
#8Re: Deep learning with text: Learning when to skim and when to read
#9cool paper, i enjoyed following the post (and really appreciated the effort put into the bokeh viz!)
i wonder if this would have been improved by being clearer about the motivation. the authors frame it as though the ~60ms penalty for using the LSTM for prediction is a huge burden, and i can imagine situations where it is. however, it seems like if this is the case, we need some real life/"scaled out" examples of how this solution would work in practice. e.g. how long does the decision logic take to execute (maybe 5ms?); what proportion of the time will you have to run the LSTM after the BoW model anyway? note that those instances you are now worse off than just running the LSTM in the first place (total time = BoW time + decision time + LSTM time). once you have all these you can run the math and know (on average) how much time you'll actually save, and how much performance you sacrifice