Key-Value Memory Networks for Directly Reading Documents

  • By :
  • Category : Dating

Directly reading documents and being able to answer questions from them is an
unsolved challenge. To avoid its inherent difficulty, question answering (QA)
has been directed towards using Knowledge Bases (KBs) instead, which has proven
effective. Unfortunately KBs often suffer from being too restrictive, as the
schema cannot support certain types of answers, and too sparse, e.g. Wikipedia
contains much more information than Freebase. In this work we introduce a new
method, Key-Value Memory Networks, that makes reading documents more viable by
utilizing different encodings in the addressing and output stages of the memory
read operation. To compare using KBs, information extraction or Wikipedia
documents directly in a single framework we construct an analysis tool,
WikiMovies, a QA dataset that contains raw text alongside a preprocessed KB, in
the domain of movies. Our method reduces the gap between all three settings. It
also achieves state-of-the-art results on the existing WikiQA benchmark.


No Comments

Leave a Reply

Your email address will not be published. Required fields are marked *

Whispering, Walking Bats Are Onto Something

Bats have a brilliant way to find prey in the dark: echolocation. But to many of the moths they eat, that natural sonar is as loud as a jet engine. So some bats have hit on a sneakier, scrappier way to hunt. See how these adorable bats are using their …

The Day Nothing Changed

Why 9/11 wasn’t another Pearl Harbor. Source:

Digital Marketing Keyword Interest Over Time

Google’s Keyword Trends tool is extremely interesting to me. Here, we can see if businesses, tactics, and more are in free fall, growth, or stagnation. We can potentially identify stock opportunities or similarly, when we should eject or short a company. We can see the interest levels in our competitor. …