Test:2019 CharacterLevelLanguageModelingw

(Al-Rfou et al., 2019) ⇒ Rami Al-Rfou, Dokook Choe, Noah Constant, Mandy Guo, and Llion Jones. (2019). “Character-Level Language Modeling with Deeper Self-Attention.” In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI 2019), The Thirty-First Innovative Applications of Artificial Intelligence Conference (IAAI 2019), The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI 2019).

Subject Headings: Character-Level Language Model.

Notes

Cited By

http://scholar.google.com/scholar?q=%222019%22+Character-Level+Language+Modeling+with+Deeper+Self-Attention

Quotes

Abstract

LSTMs and other RNN variants have shown strong performance on character-level language modeling. These models are typically trained using truncated backpropagation through time, and it is common to assume that their success stems from their ability to remember long-term contexts. In this paper, we show that a deep (64-layer) transformer model (Vaswani et al. 2017) with fixed context outperforms RNN variants by a large margin, achieving state of the art on two popular benchmarks: 1.13 bits per character on text8 and 1.06 on enwik8. To get good results at this depth, we show that it is important to add auxiliary losses, both at intermediate network layers and intermediate sequence positions.

References

BibTeX

@inproceedings{2019_CharacterLevelLanguageModelingw,
  author    = {Rami Al-Rfou and
               Dokook Choe and
               Noah Constant and
               Mandy Guo and
               Llion Jones},
  title     = {Character-Level Language Modeling with Deeper Self-Attention},
  booktitle = {Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI
               2019), The Thirty-First Innovative Applications of Artificial Intelligence
               Conference (IAAI 2019), The Ninth AAAI Symposium on Educational
               Advances in Artificial Intelligence (EAAI 2019)},
  pages     = {3159--3166},
  publisher = {AAAI Press},
  year      = {2019},
  url       = {https://doi.org/10.1609/aaai.v33i01.33013159},
  doi       = {10.1609/aaai.v33i01.33013159},
}

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2019 CharacterLevelLanguageModelingw	Rami Al-Rfou Llion Jones Dokook Choe Noah Constant Mandy Guo			Character-Level Language Modeling with Deeper Self-Attention