arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.02592cs.CLcs.LG
收藏

用于神经机器翻译的语标子词模型

Logographic Subword Model for Neural Machine Translation

McMaster University(麦克马斯特大学);Queen’s University(女王大学)

Yihao Fang, Rong Zheng, Xiaodan Zhu

摘要:

提出了一种新的语标子词模型,将语标重新解释为神经机器翻译的抽象子词。我们的方法大大减小了人工神经网络的大小,同时保持了与基线RNN和CNN seq 2seq模型相当的BLEU分数。较小的模型大小也会导致更短的训练和推理时间。实验表明,在英汉/汉英翻译任务中,这些方面的减少可以从$11\%$到高达$77\%$。与以前的子词模型相比,抽象子词可以应用于各种语标语言。考虑到大多数的语标语言是古老的和非常低的资源语言,这些优势是非常可取的考古计算语言学应用,如资源有限的离线手持人口英语翻译。

英文摘要:

A novel logographic subword model is proposed to reinterpret logograms as abstract subwords for neural machine translation. Our approach drastically reduces the size of an artificial neural network, while maintaining comparable BLEU scores as those attained with the baseline RNN and CNN seq2seq models. The smaller model size also leads to shorter training and inference time. Experiments demonstrate that in the tasks of English-Chinese/Chinese-English translation, the reduction of those aspects can be from $11\%$ to as high as $77\%$. Compared to previous subword models, abstract subwords can be applied to various logographic languages. Considering most of the logographic languages are ancient and very low resource languages, these advantages are very desirable for archaeological computational linguistic applications such as a resource-limited offline hand-held Demotic-English translator.

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。

↑