最开始提出了针对NMT的Coverage模型的论文。 #242 的先行研究。
We maintain a coverage vector to keep track of the attention history. The coverage vector is fed to the attention model to help adjust future attention, which lets NMT system to consider more about untranslated source words
一句话总结:
最开始提出了针对NMT的Coverage模型的论文。 #242 的先行研究。 We maintain a coverage vector to keep track of the attention history. The coverage vector is fed to the attention model to help adjust future attention, which lets NMT system to consider more about untranslated source words
资源:
论文信息:
笔记:
在NMT里,coverage只是为了在翻译的时候,对于source text,不添加,不遗漏,才被提出的。 而在 #242 中,主要是为了防止repeated attention 才提出的。
模型图:
结果:
接下来要看的论文: