Posts

The OntoNotes dataset, which is the focus of almost all coreference resolution research, had several compromises in its development (as is the case for any dataset). Some of these are discussed in…

Continue Reading

A common argument in favour of neural networks is that they do not require ‘feature engineering’, manually defining functions that produce useful representations of the input data (e.g. a function…

Continue Reading

Virtually all systems trained using data have trouble when applied to datasets that differ even slightly - even switching from Wall Street…

Continue Reading

We know that training a neural network involves optimising over a non-convex space, but using standard evaluation methods we see that our models…

Continue Reading

Assigning a probability distribution over the next word or character in a sequence (language modeling) is a useful component of many systems…

Continue Reading

Being able to query a database in natural language could help make data accessible …

Continue Reading

Reordering training sentences for word vectors may impact their usefulness for downstream tasks.

Continue Reading

With enough training data, the best vector representation of a sentence is to concatenate an average over word vectors and an average over character trigram vectors.

Continue Reading

For a more flexible dialogue system, use the crowd to propose and vote on responses, then introduce agents and a model for voting, gradually learning to replace the crowd.

Continue Reading

To leverage out-of-domain data, learn multiple sets of word vectors but with a loss term that encourages them to be similar.

Continue Reading