按年被提到
20162016 · 2 次2026
大模型与语言模型›序列模型与注意力机制·arXiv:1610.03017 · cs.CL

Fully Character-Level Neural Machine Translation without Explicit Segmentation

Jason Lee, Kyunghyun Cho, Thomas Hofmann · 2016
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 4 人首次 2016-10-11 · 最近 2017-01-02
4不同的人
2活跃月份
4讨论串
396被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character sequence without any segmentation. We employ a character-level convolutional network with max-pooling at the encoder to reduce the length of source representation, allowing the model to be trained at a speed comparable to subword-level models while capturing local regularities. Our character-to-character model outperforms a recently proposed baseline with a subword-level encoder on WMT'15 DE-EN and CS-EN, and gives comparable performance on FI-EN and RU-EN. We then demonstrate that it is possible to share a single character-level encoder across multiple languages by training a model on a many-to-one translation task. In this multilingual setting, the character-level encoder significantly outperforms the subword-level encoder on all the language pairs. We observe that on CS-EN, FI-EN and RU-EN, the quality of the multilingual character-level translation even surpasses the models specifically trained on that language pair alone, both in terms of BLEU score and human judgment.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论stared · 2017-01

“Seconding it with: https://arxiv.org/abs/1610.03017 Fully Character-Level Neural Machine Translation without Explicit Segmentation. In general, RNNs are especially fit for discrete sequences. And their continuous representation is actually an advantage (so they can see that two words are similar or analogous). BTW: see my draft on word2vec: http://p.migd…”

Why Deep Learning Cannot Be Applied to Natural Languages Easily原评论 ↗
被提交为 story · 3 次