We perform an effective-theory analysis of forward-backward signal
propa...
Despite many recent advancements in language modeling, state-of-the-art
...
Existing approaches built separate classifiers to detect nonsense in
dia...
Deployed dialogue agents have the potential to integrate human feedback ...
Over the last several years, end-to-end neural conversational agents hav...
Open-domain dialogue agents have vastly improved, but still confidently
...
Models trained on large unlabeled corpora of human interactions will lea...
Open-domain conversation models have become good at generating
natural-s...
Much of NLP research has focused on crowdsourced static datasets and the...
We present our view of what is necessary to build an engaging open-domai...
Machine learning models are trained to find patterns in data. NLP models...
Building open-domain chatbots is a challenging area for machine learning...
Dialogue research tends to distinguish between chit-chat and goal-orient...
Dialogue research tends to distinguish between chit-chat and goal-orient...
Procedurally generating cohesive and interesting game environments is
ch...
Text style transfer is usually performed using attributes that can take ...
Models often easily learn biases present in the training data, and their...
We introduce dodecaDialogue: a set of 12 tasks that measures if a
conver...
We introduce a new large-scale NLI benchmark dataset, collected via an
i...
The detection of offensive language in the context of a dialogue has bec...
Neural text generation is a key tool in natural language applications, b...
We introduce a large scale crowdsourced text adventure game as a researc...
We describe the setting and results of the ConvAI2 NeurIPS competition t...
In open-domain dialogue intelligent agents should exhibit the use of
kno...
Sequence generation models for dialogue are known to have several proble...
Chit-chat models are known to have several problems: they lack specifici...