arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.00563cs.CL
收藏

神经MT搜索和模型性能分析

Analyzing Neural MT Search and Model Performance

Institute for Anthropomatics and Robotics(人体测量学与机器人研究所);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Jan Niehues, Eunah Cho, Thanh-Le Ha, Alex Waibel

摘要:

在本文中,我们提供了一个深入的分析建模和搜索性能。我们解决的问题,如果一个更复杂的搜索算法是必要的。此外,我们调查的问题,如果更复杂的模型,可能只适用于重新评分是有前途的。通过分离搜索空间和建模使用$n$ -最佳列表重排,我们分析了NMT系统的两个部分的影响独立。通过比较不同性能的NMT系统,我们表明,更好的翻译已经在搜索空间的翻译系统的性能较低。这一结果表明,目前的搜索算法是足够的NMT系统。此外,我们可以证明,即使是一个相对较小的$n$ -$50$假设的最佳列表也已经包含了明显更好的翻译。

英文摘要:

In this paper, we offer an in-depth analysis about the modeling and search performance. We address the question if a more complex search algorithm is necessary. Furthermore, we investigate the question if more complex models which might only be applicable during rescoring are promising. By separating the search space and the modeling using $n$-best list reranking, we analyze the influence of both parts of an NMT system independently. By comparing differently performing NMT systems, we show that the better translation is already in the search space of the translation systems with less performance. This results indicate that the current search algorithms are sufficient for the NMT systems. Furthermore, we could show that even a relatively small $n$-best list of $50$ hypotheses already contain notably better translations.

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。

↑