A Prospective-Performance Network to Alleviate Myopia in Beam Search for Response Generation

COLING 2018 · Zongsheng Wang, Yunzhi Bai, Bowen Wu, Zhen Xu, Zhuoran Wang, Baoxun Wang ·

Generative dialog models usually adopt beam search as the inference method to generate responses. However, small-width beam search only focuses on the limited current optima. This deficiency named as myopic bias ultimately suppresses the diversity and probability of generated responses. Although increasing the beam width mitigates the myopic bias, it also proportionally slows down the inference efficiency. To alleviate the myopic bias in small-width beam search, this paper proposes a Prospective-Performance Network (PPN) to predict the future reward of the given partially-generated response, and the future reward is defined by the expectation of the partial response appearing in the top-ranked responses given by a larger-width beam search. Enhanced by PPN, the decoder can promote the results with great potential during the beam search phase. The experimental results on both Chinese and English corpora show that our method is promising to increase the quality and diversity of generated responses, with inference efficiency well maintained.