Yuta Kikuchi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuta Kikuchi has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Hiroya Takamura
National Institute of Advanced Industrial Science and Technology
2 shared publications Manabu Okumura
2 shared publicationsAkihiko Watanabe
Tokyo Institute of Technology
1 shared publication- Graham Neubig
Carnegie Mellon University, Pittsburgh, Pennsylvania, USA
1 shared publication - Ryohei Sasano
Tokyo Institute of Technology
1 shared publication Sasano Ryohei
Tokyo Institute of Technology
1 shared publication
Latest Publications
- Open Access
Controlling Output Length in Neural Encoder-Decoders
Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not investigated situations in which we would like to control the length of encoder-decoder outputs. This capability is crucial for applications such as text summarization, in which we have to generate concise summaries with a desired length. In this paper, we propose methods for controlling the output sequence length for neural encoder-decoder models: two decoding-based methods and two learning-based methods. Results show that our learning-based methods have the capability to control length without degrading summary quality in a summarization task.
Open AccessControlling Output Length in Neural Encoder-Decoders
Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not investigated situations in which we would like to control the length of encoder-decoder outputs. This capability is crucial for applications such as text summarization, in which we have to generate concise summaries with a desired length. In this paper, we propose methods for controlling the output sequence length for neural encoder-decoder models: two decoding-based methods and two learning-based methods. Results show that our learning-based methods have the capability to control length without degrading summary quality in a summarization task.
- 10 August 2016
- Published by Springer Nature
- p. 206-219
Learning from Numerous Untailored Summaries