arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.03053cs.CLcs.AIcs.LG
收藏

神经机器翻译的大动作空间强化学习

Reinforcement Learning with Large Action Spaces for Neural Machine Translation

The Hebrew University of Jerusalem(耶路撒冷希伯来大学)

Asaf Yehudai, Leshem Choshen, Lior Fox, Omri Abend

摘要:

在最大似然估计(MLE)预训练之后应用强化学习(RL)是用于增强神经机器翻译(NMT)性能的通用方法。然而,最近的研究认为,RL为NMT带来的收益主要是由于提升了在预训练中已经获得相当高概率的令牌。我们假设大的动作空间是RL在机器翻译中有效性的主要障碍,并进行了两组实验来支持我们的假设。首先,我们发现减少词汇量可以提高RL的有效性。其次,我们发现,有效地减少行动空间的维度,而不改变词汇也产生了显着的改善,由BLEU,语义相似性,和人类的评价。事实上,通过初始化网络的最终全连接层(将网络的内部维度映射到词汇维度),并使用一个对类似动作进行泛化的层,我们获得了RL性能的实质性改善:平均1.5个BLEU点。

英文摘要:

Applying Reinforcement learning (RL) following maximum likelihood estimation (MLE) pre-training is a versatile method for enhancing neural machine translation (NMT) performance. However, recent work has argued that the gains produced by RL for NMT are mostly due to promoting tokens that have already received a fairly high probability in pre-training. We hypothesize that the large action space is a main obstacle to RL's effectiveness in MT, and conduct two sets of experiments that lend support to our hypothesis. First, we find that reducing the size of the vocabulary improves RL's effectiveness. Second, we find that effectively reducing the dimension of the action space without changing the vocabulary also yields notable improvement as evaluated by BLEU, semantic similarity, and human evaluation. Indeed, by initializing the network's final fully connected layer (that maps the network's internal dimension to the vocabulary dimension), with a layer that generalizes over similar actions, we obtain a substantial improvement in RL performance: 1.5 BLEU points on average.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑