SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1706.05087 · 2017

Plan, Attend, Generate: Character-level Neural Machine Translation with Planning in the Decoder

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

We investigate the integration of a planning mechanism into an encoder-decoder architecture with an explicit alignment for character-level machine translation. We develop a model that plans ahead when it computes alignments between the source and target sequences, constructing a matrix of proposed future alignments and a commitment vector that governs whether to follow or recompute the plan. This mechanism is inspired by the strategic attentive reader and writer (STRAW) model. Our proposed model is end-to-end trainable with fully differentiable operations. We show that it outperforms a strong baseline on three character-level decoder neural machine translation on WMT'15 corpus. Our analysis demonstrates that our model can compute qualitatively intuitive alignments and achieves superior performance with fewer parameters.

For agents

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

get_harvested_code_for_paper("1706.05087")
get_code_for_paper("1706.05087")
have("1706.05087")

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

curl https://syntology.ai/api/ran/1706.05087.json

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

[![Syntology run record](https://syntology.ai/api/ran/1706.05087.svg)](https://syntology.ai/paper/1706.05087)

Connect an agent — have() is free.