Publications

CONFERENCE (INTERNATIONAL) 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)

February 01, 2019

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.

Paper : Neural Headline Generation with Self-Trainingopen into new tab or window (external link)

PDF : Neural Headline Generation with Self-Training