2018/11/01 by Cho, Woon Sang, Zhang, Pengchuan, Zhang, Yizhe +5
#Computation and Language (cs.CL) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.1811.00511
Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models from the perspectives of coherence and cohesion. In this work, we propose a new neural language model that is equipped with two neural discriminators which provide feedback signals at the levels of sentence (cohesion) and paragraph (coherence). Our model is trained using a simple yet efficient variant of policy gradient, called negative-critical sequence training, which is proposed to eliminate the need of training a separate critic for estimating baseline. Results demonstrate the effectiveness of our approach, showing improvements over the strong baseline -- recurrent attention-based bidirectional MLE-trained neural language model.