Instruction tuning has emerged as a promising approach to enhancing larg...
While large-scale neural language models, such as GPT2 and BART, have
ac...
Sentence function is an important linguistic feature indicating the
comm...
Maintaining a consistent attribute profile is crucial for dialogue agent...
Most of the existing works for dialogue generation are data-driven model...
With the rapid prevalence and explosive development of MOBA esports
(Mul...
Neural conversation models are known to generate appropriate but
non-inf...
Variational Autoencoder (VAE) is widely used as a generative model to
ap...
Neural text generation has made tremendous progress in various tasks. On...
Maintaining a consistent personality in conversations is quite natural f...
Response selection plays a vital role in building retrieval-based
conver...
The ability of a dialog system to express prespecified language style du...
Stylistic response generation is crucial for building an engaging dialog...
In this paper, we focus on a new practical task, document-scale text con...
Neural network models usually suffer from the challenge of incorporating...
Despite the effectiveness of sequence-to-sequence framework on the task ...
Neural conversation models such as encoder-decoder models are easy to
ge...
Embedding from Language Models (ELMo) has shown to be effective for impr...
Sentence function is an important linguistic feature referring to a user...
Neural generative models have become popular and achieved promising
perf...
Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to
...
For dialogue response generation, traditional generative models generate...
Language style transfer is the problem of migrating the content of a sou...
Comments of online articles provide extended views and improve user
enga...
We study the problem of stock related question answering (StockQA):
auto...