Automatic Post-Editing
25 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.
Benchmarks
These leaderboards are used to track progress in Automatic Post-Editing
Datasets
eSCAPE
WMT 2016 News
WMT 2018 News
SubEdits
DivEMT
WMT 2016 IT
WMT 2016 Biomedical
WMT 2015 News
APE
Latest papers
Automatic Correction of Human Translations
We show that human errors in TEC exhibit a more diverse range of errors and far fewer translation fluency errors than the MT errors in automatic post-editing datasets, suggesting the need for dedicated TEC models that are specialized to correct human errors.
Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study
osu-nlp-group/llm-cn-eval
•
•
Findings (ACL) 2022
In this work, we present an extensive study on the use of pre-trained language models for the task of automatic Counter Narrative (CN) generation to fight online hate speech in English.
Transfer Learning for Sequence Generation: from Single-source to Multi-source
Although directly finetuning pretrained models on MSG tasks and concatenating multiple sources into a single long sequence is regarded as a simple method to transfer pretrained models to MSG tasks, we conjecture that the direct finetuning method leads to catastrophic forgetting and solely relying on pretrained self-attention layers to capture cross-source information is not sufficient.
Automatic Post-Editing for Vietnamese
Automatic post-editing (APE) is an important remedy for reducing errors of raw translated texts that are produced by machine translation (MT) systems or software-aided translation.
Adaptation of Back-translation to Automatic Post-Editing for Synthetic Data Generation
Automatic Post-Editing (APE) aims to correct errors in the output of a given machine translation (MT) system.
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.
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).
Can Automatic Post-Editing Improve NMT?
To ascertain our hypothesis, we compile a larger corpus of human post-edits of English to German NMT.
DynE: Dynamic Ensemble Decoding for Multi-Document Summarization
chrishokamp/dynamic-transformer-ensembles
•
•
Sequence-to-sequence (s2s) models are the basis for extensive work in natural language processing.
Learning Non-Monotonic Automatic Post-Editing of Translations from Human Orderings
Recent research in neural machine translation has explored flexible generation orders, as an alternative to left-to-right generation.
