[3Pin1] インタラクティブ(1)

[3Pin1-36] Neural Headline Generation with Self-Training

Shintaro Takemae², Kazuma Murao¹, 〇Taichi Yatsuka¹, Hayato Kobayashi^1,3, Masaki Noguchi¹, Hitoshi Nishikawa², Takenobu Tokunaga² (1. Yahoo Japan Corporation, 2. Tokyo Institute of Technology, 3. RIKEN AIP)

Keywords:Summarization, Self-training, Neural Network

In this paper we propose a novel method which incorporates self-training into a sequence-to-sequence model in order to improve the accuracy of the headline generation task. Our model is based on neural network-based sequence-to-sequence learning with an attention mechanism and trained with approximately 100,000 labeled examples and 2,000,000 unlabeled examples. Through experiments, we show our proposal significantly improves the accuracy and works effectively.