Reinforcement Learning for Improved Low Resource Dialogue Generation

AAAI 2019 pp. 9884-9885

doi:10.1609/AAAI.V33I01.33019884 /aaai/2019/gonzalezgarduno2019aaai-reinforcement/

Abstract

In this thesis, I focus on language independent methods of improving utterance understanding and response generation and attempt to tackle some of the issues surrounding current systems. The aim is to create a unified approach to dialogue generation inspired by developments in both goal oriented and open ended dialogue systems. The main contributions in this thesis are: 1) Introducing hybrid approaches to dialogue generation using retrieval and encoder-decoder architectures to produce fluent but precise utterances in dialogues, 2) Proposing supervised, semi-supervised and Reinforcement Learning methods for domain adaptation in goal oriented dialogue and 3) Introducing models that can adapt cross lingually.

PDF AAAI Semantic Scholar

Cite

Text

González-Garduño. "Reinforcement Learning for Improved Low Resource Dialogue Generation." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33019884

Markdown

[González-Garduño. "Reinforcement Learning for Improved Low Resource Dialogue Generation." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/gonzalezgarduno2019aaai-reinforcement/) doi:10.1609/AAAI.V33I01.33019884

BibTeX

@inproceedings{gonzalezgarduno2019aaai-reinforcement,
  title     = {{Reinforcement Learning for Improved Low Resource Dialogue Generation}},
  author    = {González-Garduño, Ana Valeria},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {9884-9885},
  doi       = {10.1609/AAAI.V33I01.33019884},
  url       = {https://mlanthology.org/aaai/2019/gonzalezgarduno2019aaai-reinforcement/}
}