SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1711.09367 · 2017

Learning to Remember Translation History with a Continuous Cache

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1711.09367")
get_code_for_paper("1711.09367")
have("1711.09367")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1711.09367.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1711.09367.svg)](https://syntology.ai/paper/1711.09367)

Connect an agent — have() is free.