Comparison of assorted models for transliteration
Proceedings of the Seventh Named Entities Workshop, 2018•aclanthology.org
We report the results of our experiments in the context of the NEWS 2018 Shared Task on
Transliteration. We focus on the comparison of several diverse systems, including three
neural MT models. A combination of discriminative, generative, and neural models obtains
the best results on the development sets. We also put forward ideas for improving the shared
task.
Transliteration. We focus on the comparison of several diverse systems, including three
neural MT models. A combination of discriminative, generative, and neural models obtains
the best results on the development sets. We also put forward ideas for improving the shared
task.
Abstract
We report the results of our experiments in the context of the NEWS 2018 Shared Task on Transliteration. We focus on the comparison of several diverse systems, including three neural MT models. A combination of discriminative, generative, and neural models obtains the best results on the development sets. We also put forward ideas for improving the shared task.
aclanthology.org
以上显示的是最相近的搜索结果。 查看全部搜索结果