Neural Headline Generation with Self-Training

Kazuma Murao, Shintaro Takemae, Hayato Kobayashi, Taichi Yatsuka, Masaki Noguchi, Hitoshi Nishikawa (Tokyo Tech), and Takenobu Tokunaga (Tokyo Tech)

Computation Journalism 2019 (CJ2019), 2019/2


Natural Language Processing

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 baseline 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 ex- periments, we show our proposal signi cantly improves the accu- racy and works e ectively.

Neural Headline Generation with Self-Training(External Site Link)