Multi-Agent Dual Learning
Multi-Agent Dual Learning
复制标题
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Yiren Wang;Yingce Xia;Tianyu He;Fei Tian;Tao Qin;Chengxiang Zhai;Tie-Yan Liu
中科院分区：
文献类型：
--
作者：
Yiren Wang;Yingce Xia;Tianyu He;Fei Tian;Tao Qin;Chengxiang Zhai;Tie-Yan Liu
对偶学习在机器学习、计算机视觉和自然语言处理领域备受关注。对偶学习的核心思想是利用原始任务(从X域到Y域的映射)和双重任务(从Y域到X的映射)之间的对偶性来提高这两个任务的性能。现有的对偶学习框架形成了一个由两个代理(一个原始模型和一个对偶模型)组成的系统来利用这种二元性。在本文中，我们通过引入多个原始模型和对偶模型对该框架进行了扩展，提出了多智能体对偶学习框架。在神经机器翻译和图像翻译任务上的实验证明了新框架的有效性。特别是，我们在2014WWSLT德英翻译中以35.44%的BLEU得分刷新了纪录，在2014WMT中BLEU的得分达到31.03%，BLEU在强大的变形金刚基准上提高了2.6%以上，在最近的2018年WMT 2018年英译德语中创造了49.61WMT的BLEU得分的新纪录。
Dual learning has attracted much attention in machine learning, computer vision and natural language processing communities. The core idea of dual learning is to leverage the duality between the primal task (mapping from domain X to domain Y) and dual task (mapping from domain Y to X ) to boost the performances of both tasks. Existing dual learning framework forms a system with two agents (one primal model and one dual model) to utilize such duality. In this paper, we extend this framework by introducing multiple primal and dual models, and propose the multi-agent dual learning framework. Experiments on neural machine translation and image translation tasks demonstrate the effectiveness of the new framework. In particular, we set a new record on IWSLT 2014 German-to-English translation with a 35.44 BLEU score, achieve a 31.03 BLEU score on WMT 2014 English-toGerman translation with over 2.6 BLEU improvement over the strong Transformer baseline, and set a new record of 49.61 BLEU score on the recent WMT 2018 English-to-German translation.