Emotion recognition in conversation: Research challenges, datasets, and recent advances

S Poria, N Majumder, R Mihalcea, E Hovy - IEEE access, 2019 - ieeexplore.ieee.org
Emotion is intrinsic to humans and consequently, emotion understanding is a key part of
human-like artificial intelligence (AI). Emotion recognition in conversation (ERC) is …

Survey of the state of the art in natural language generation: Core tasks, applications and evaluation

A Gatt, E Krahmer - Journal of Artificial Intelligence Research, 2018 - jair.org
This paper surveys the current state of the art in Natural Language Generation (NLG),
defined as the task of generating text or speech from non-linguistic input. A survey of NLG is …

Dear sir or madam, may I introduce the GYAFC dataset: Corpus, benchmarks and metrics for formality style transfer

S Rao, J Tetreault - arxiv preprint arxiv:1803.06535, 2018 - arxiv.org
Style transfer is the task of automatically transforming a piece of text in one particular style
into another. A major barrier to progress in this field has been a lack of training and …

Controlling linguistic style aspects in neural language generation

J Ficler, Y Goldberg - arxiv preprint arxiv:1707.02633, 2017 - arxiv.org
Most work on neural natural language generation (NNLG) focus on controlling the content of
the generated text. We experiment with controlling several stylistic aspects of the generated …