End-to-end task-oriented dialogue (TOD) systems have achieved promising
...
We present a theory for the previously unexplained divergent behavior no...
Generative language models define distributions over sequences of tokens...
We present BlenderBot 3, a 175B parameter dialogue model capable of
open...
Large language models, which are often trained for hundreds of thousands...
Language models (LMs) have recently been shown to generate more factual
...
At the heart of improving conversational AI is the open problem of how t...
We demonstrate that large language models are able to simulate Task Orie...
We investigate the training of sparse layers that use different paramete...
Attention mechanisms have become a standard tool for sequence modeling t...
Attention mechanisms have shown promising results in sequence modeling t...
The existing dialogue corpora and models are typically designed under tw...
We present our view of what is necessary to build an engaging open-domai...
Building open-domain chatbots is a challenging area for machine learning...
Generative dialogue models currently suffer from a number of problems wh...
We introduce dodecaDialogue: a set of 12 tasks that measures if a
conver...
While dialogue remains an important end-goal of natural language researc...
Neural text generation is a key tool in natural language applications, b...
A good conversation requires balance -- between simplicity and detail;
s...
We consider the task of inferring is-a relationships from large text cor...
In open-domain dialogue intelligent agents should exhibit the use of
kno...
Methods for unsupervised hypernym detection may broadly be categorized
a...
We test whether distributional models can do one-shot learning of
defini...
We consider the task of predicting lexical entailment using distribution...
We introduce a novel, simple convolution neural network (CNN) architectu...