top | item 20470401

A Breakthrough in Temporal Expression Understanding

13 points| caente | 6 years ago |x.ai

6 comments

order

marjimbel|6 years ago

marcos here (one of the authors). i know the word "breakthrough" in the title is a "little" ambitious, but i really think we've done something interesting ... we'd like to publish so this is a way to collect questions/comments! soot away.

wistfully|6 years ago

Do you filter out garbage lines in emails prior to setting up for training or you include the entire email?

marjimbel|6 years ago

the memory blows up with the length of encoder sequence. for that reason we truncate the email at ~300 tokens, which is for the vast majority of cases enough to capture the relevant info. other than that we don't get rid of any "garbage" lines. instead, we let the NN (eg. the attention layer) figure out which lines are irrelevant