Deep reinforcement learning (RL) has been a commonly-used strategy for the
abstractive summarization task to address both the exposure bias and
non-differentiable task issues. However, the conventional reward Rouge-L simply
looks for exact n-grams matches between candidates and annotated references,
which inevitably makes the generated sentences repetitive and incoherent. In
this paper, instead of Rouge-L, we explore the practicability of utilizing the
distributional semantics to measure the matching degrees. With distributional
semantics, sentence-level evaluation can be obtained, and semantically-correct
phrases can also be generated without being limited to the surface form of the
reference sentences. Human judgments on Gigaword and CNN/Daily Mail datasets
show that our proposed distributional semantics reward (DSR) has distinct
superiority in capturing the lexical and compositional diversity of natural
language.

本研究论文使用分布式语义学方法，提出了一种新的奖励制度 DSR (Distributional Semantics Reward)，用于评估候选摘要的性能，与传统的奖励模式相比，DSR 可以更准确地捕捉自然语言的词汇和构成多样性。