Automatic Post-Editing

24 papers with code • 0 benchmarks • 10 datasets

Automatic post-editing (APE) is used to correct errors in the translation made by the machine translation systems.

Most implemented papers

A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning

deep-spin/OpenNMT-APE 14 Jun 2019

Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits.

A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning

deep-spin/OpenNMT-APE ACL 2019

Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits.

Context-Aware Monolingual Repair for Neural Machine Translation

lena-voita/good-translation-wrong-in-context IJCNLP 2019

For training, the DocRepair model requires only monolingual document-level data in the target language.

Deep Copycat Networks for Text-to-Text Generation

ImperialNLP/CopyCat IJCNLP 2019

Most text-to-text generation tasks, for example text summarisation and text simplification, require copying words from the input to the output.

Learning Non-Monotonic Automatic Post-Editing of Translations from Human Orderings

antoniogois/keystrokes_ape EAMT 2020

Recent research in neural machine translation has explored flexible generation orders, as an alternative to left-to-right generation.

DynE: Dynamic Ensemble Decoding for Multi-Document Summarization

chrishokamp/dynamic-transformer-ensembles 15 Jun 2020

Sequence-to-sequence (s2s) models are the basis for extensive work in natural language processing.

Can Automatic Post-Editing Improve NMT?

shamilcm/pedra EMNLP 2020

To ascertain our hypothesis, we compile a larger corpus of human post-edits of English to German NMT.

MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset

sheffieldnlp/mlqe-pe LREC 2022

We present MLQE-PE, a new dataset for Machine Translation (MT) Quality Estimation (QE) and Automatic Post-Editing (APE).

Incorporating Terminology Constraints in Automatic Post-Editing

zerocstaker/constrained_ape WMT (EMNLP) 2020

In this paper, we present both autoregressive and non-autoregressive models for lexically constrained APE, demonstrating that our approach enables preservation of 95% of the terminologies and also improves translation quality on English-German benchmarks.

Adaptation of Back-translation to Automatic Post-Editing for Synthetic Data Generation

wonkeelee/ape-backtranslation EACL 2021

Automatic Post-Editing (APE) aims to correct errors in the output of a given machine translation (MT) system.