arXiv Open Access 2017

Learning to Remember Translation History with a Continuous Cache

Zhaopeng Tu Yang Liu Shuming Shi Tong Zhang

Lihat Sumber

Abstrak

Existing neural machine translation (NMT) models generally translate sentences in isolation, missing the opportunity to take advantage of document-level information. In this work, we propose to augment NMT models with a very light-weight cache-like memory network, which stores recent hidden representations as translation history. The probability distribution over generated words is updated online depending on the translation history retrieved from the memory, endowing NMT models with the capability to dynamically adapt over time. Experiments on multiple domains with different topics and styles show the effectiveness of the proposed approach with negligible impact on the computational cost.

Topik & Kata Kunci

cs.CL

Penulis (4)

Zhaopeng Tu

Yang Liu

Shuming Shi

Tong Zhang

Format Sitasi

APA MLA BibTeX

Tu, Z., Liu, Y., Shi, S., Zhang, T. (2017). Learning to Remember Translation History with a Continuous Cache. https://arxiv.org/abs/1711.09367

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2017
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓