ML Anthology

Transformer-Capsule Model for Intent Detection (Student Abstract)

Aleksander Obuchowski, Michal Lew
AAAI 2020 pp. 13885-13886
doi:10.1609/AAAI.V34I10.7215 /aaai/2020/obuchowski2020aaai-transformer/

Abstract

Intent recognition is one of the most crucial tasks in NLU systems, which are nowadays especially important for designing intelligent conversation. We propose a novel approach to intent recognition which involves combining transformer architecture with capsule networks. Our results show that such architecture performs better than original capsule-NLU network implementations and achieves state-of-the-art results on datasets such as ATIS, AskUbuntu ,and WebApp.

PDF AAAI Semantic Scholar

Cite

Text

Obuchowski and Lew. "Transformer-Capsule Model for Intent Detection (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7215

Markdown

[Obuchowski and Lew. "Transformer-Capsule Model for Intent Detection (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/obuchowski2020aaai-transformer/) doi:10.1609/AAAI.V34I10.7215

BibTeX

@inproceedings{obuchowski2020aaai-transformer,
  title     = {{Transformer-Capsule Model for Intent Detection (Student Abstract)}},
  author    = {Obuchowski, Aleksander and Lew, Michal},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13885-13886},
  doi       = {10.1609/AAAI.V34I10.7215},
  url       = {https://mlanthology.org/aaai/2020/obuchowski2020aaai-transformer/}
}