Revisiting the Markov Property for Machine Translation
Conference of the European Chapter of the Association for Computational Linguistics(2024)
摘要
In this paper, we re-examine the Markov property in the context of neural
machine translation. We design a Markov Autoregressive Transformer (MAT) and
undertake a comprehensive assessment of its performance across four WMT
benchmarks. Our findings indicate that MAT with an order larger than 4 can
generate translations with quality on par with that of conventional
autoregressive transformers. In addition, counter-intuitively, we also find
that the advantages of utilizing a higher-order MAT do not specifically
contribute to the translation of longer sentences.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要