Agency, the capacity to proactively shape events, is crucial to how huma...
We introduce GODEL (Grounded Open Dialogue Language Model), a large
pre-...
The advent of large pre-trained language models has made it possible to ...
Recent advances in large-scale pre-training such as GPT-3 allow seemingl...
Large pretrained generative models like GPT-3 often suffer from hallucin...
A prevailing paradigm in neural text generation is one-shot generation, ...
Adversarial examples expose the vulnerabilities of natural language
proc...
Existing open-domain dialog models are generally trained to minimize the...
Many high-level procedural tasks can be decomposed into sequences of
ins...
Current end-to-end neural conversation models inherently lack the flexib...
Large-scale pre-trained language models, such as BERT and GPT-2, have
ac...
We present a large, tunable neural conversational response generation mo...
Ambiguous user queries in search engines result in the retrieval of docu...
Generating responses in a targeted style is a useful yet challenging tas...
Text style transfer without parallel data has achieved some practical
su...
Although neural conversation models are effective in learning how to pro...
Generating responses that are consistent with the dialogue context is on...
Although recent neural conversation models have shown great potential, t...
This paper introduces the Seventh Dialog System Technology Challenges (D...
We present Vision-based Navigation with Language-based Assistance (VNLA)...
Responses generated by neural conversational models tend to lack
informa...
Building a persona-based conversation agent is challenging owing to the ...
We propose simple and flexible training and decoding methods for influen...
Neural network models are capable of generating extremely natural soundi...
The popularity of image sharing on social media and the engagement it cr...
Conversational agents ("bots") are beginning to be widely used in
conver...
We present persona-based models for handling the issue of speaker consis...
Sequence-to-sequence neural network models for generation of conversatio...
We introduce Discriminative BLEU (deltaBLEU), a novel metric for intrins...
We present a novel response generation system that can be trained end to...