AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

A Dataset for Low-Resource Stylized Sequence-to-Sequence Generation

Yu Wu, Yunli Wang, Shujie Liu

AAAI 2020 · Architectures and efficiency › RNNs and normalization · approach: Non-autoregressive translation · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
end-to-end teacher-student instead of pivot pipeline (Pivotmodel)stylized S2S on MTFC · MTFC testBLEU: 38.75 -> 40.07Improved
back-translation instead of pivot pipeline (Pivotmodel)stylized S2S on MTFC · MTFC testBLEU: 38.75 -> 40.68Improved
back-translation instead of teacher-studentstylized S2S on MTFC · MTFC testhuman formality: 0.57 -> 0.46Hurt
rewrite pivot output with rules (Pivotrule) vs model pivot, human overall (ablation)pivot-based method · MTFC testhuman overall rank score: 2.76 -> 3.14Improved
teacher-student instead of pivot pipelinestylized S2S on TCFC · TCFC testhuman overall rank score: 3.47 -> 4.10Improved
back-translation instead of teacher-studentstylized S2S on TCFC · TCFC testDistinct-1: 0.052 -> 0.113Improved
back-translation instead of teacher-studentstylized S2S on TCFC · TCFC testautomatic formality: 0.862 -> 0.844Hurt
longer source sentencesall baselines · MTFC testBLEUHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy