Tracking the World State with Recurrent Entity Networks

We introduce a new model, the Recurrent Entity Network (EntNet). It is
equipped with a dynamic long-term memory which allows it to maintain and update
a representation of the state of the world as it receives new data. For
language understanding tasks, it can reason on-the-fly as it reads text, not
just when it is required to answer a question or respond as is the case for a
Memory Network (Sukhbaatar et al., 2015). Like a Neural Turing Machine or
Differentiable Neural Computer (Graves et al., 2014; 2016) it maintains a fixed
size memory and can learn to perform location and content-based read and write
operations. However, unlike those models it has a simple parallel architecture
in which several memory locations can be updated simultaneously. The EntNet
sets a new state-of-the-art on the bAbI tasks, and is the first method to solve
all the tasks in the 10k training examples setting. We also demonstrate that it
can solve a reasoning task which requires a large number of supporting facts,
which other methods are not able to solve, and can generalize past its training
horizon. It can also be practically used on large scale datasets such as
Children’s Book Test, where it obtains competitive performance, reading the
story in a single pass.


No Comments

Leave a Reply

Your email address will not be published.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

Curious arctic fox kits discover (and destroy) a motion-sensor camera

Watch a pack of curious and adorable arctic fox kits as they frolic and play… and as they discover and destroy a motion-sensor camera put in place by a filmmaker. It’s a clip from PBS Nature’s Fox Tales. Plus, more about these tundra-based mammals from Wikipedia: The Arctic fox lives …

Why Do You Care How Much Other People Work? Revisited

Basically, you shouldn’t. Source:

How I Improved My Public Speaking

In mid 2011, I had what was really my first speaking gig, at SMX Advanced, about link building. I had done a link building clinic before 10 or so people before, but this was the first serious thing I had done – talking before 200-300 some odd internet marketers in …