Browse State-of-the-Art › Automatic Post-Editing

Automatic Post-Editing

26 papers with code · 0 benchmarks · 10 datasets archive 2025-07-28

Computer Vision

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

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

10 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 124 · with a code link: 26 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (4 of 124 tagged: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 124, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

  • We achieve this by decomposing the text-editing task into two sub-tasks: tagging to decide on the subset of input tokens and their order in the output text and insertion to in-fill the missing tokens in the output not…
  • 27 May 2019 3 repositories listed
    We further confirm the flexibility of our model by showing a Levenshtein Transformer trained by machine translation can straightforwardly be used for automatic post-editing.
  • 9 Nov 2019 2 repositories listed
    To better identify translation errors, our method learns the representations of source sentences and system outputs in an interactive way.
  • 22 Sep 2024 1 repository listed
    To enhance the quality of error annotations predicted by LLM evaluators, we introduce a universal and training-free framework, MQM-APE, based on the idea of filtering out non-impactful errors by Automatically…
  • 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…
  • 4 Apr 2022 1 repository listed
    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.
  • 31 May 2021 1 repository listed
    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…
  • 1 May 2021 1 repository listed
    They also highlight blind spots in automatic methods for targeted evaluation and demonstrate the need for human assessment to evaluate document-level translation quality reliably.
  • 25 Apr 2021 1 repository listed
    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.
  • 1 Apr 2021 1 repository listed
    Automatic Post-Editing (APE) aims to correct errors in the output of a given machine translation (MT) system.
  • 19 Oct 2020 1 repository listed
    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…
  • 9 Oct 2020 1 repository listed
    We present MLQE-PE, a new dataset for Machine Translation (MT) Quality Estimation (QE) and Automatic Post-Editing (APE).
  • 30 Sep 2020 1 repository listed
    To ascertain our hypothesis, we compile a larger corpus of human post-edits of English to German NMT.
  • Sequence-to-sequence (s2s) models are the basis for extensive work in natural language processing.
  • 29 Apr 2020 1 repository listed
    Recent research in neural machine translation has explored flexible generation orders, as an alternative to left-to-right generation.
  • 1 Nov 2019 1 repository listed
    Most text-to-text generation tasks, for example text summarisation and text simplification, require copying words from the input to the output.
  • 3 Sep 2019 1 repository listed
    For training, the DocRepair model requires only monolingual document-level data in the target language.
  • 1 Jul 2019 1 repository listed
    Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits.
  • Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits.
  • 1 Oct 2018 1 repository listed
    Automated Post-Editing (PE) is the task of automatically correct common and repetitive errors found in machine translation (MT) output.
  • 1 Jul 2018 1 repository listed
    Automatic post-editing (APE) systems aim to correct the systematic errors made by machine translators.
  • 1 Jul 2018 1 repository listed
    Transliterating named entities from one language into another can be approached as neural machine translation (NMT) problem, for which we use deep attentional RNN encoder-decoder models.
  • 1 May 2018 1 repository listed
  • 15 Jun 2017 1 repository listed
    This work presents a novel approach to Automatic Post-Editing (APE) and Word-Level Quality Estimation (QE) using ensembles of specialized Neural Machine Translation (NMT) systems.
  • 21 Apr 2017 1 repository listed
    Modeling attention in neural multi-source sequence-to-sequence learning remains a relatively unexplored area, despite its usefulness in tasks that incorporate multiple source languages or modalities.
  • 1 Jun 2016 1 repository listed
  • Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing
    28 Jan 2025 0 repositories listed
    Automatic Post-Editing (APE) systems often struggle with over-correction, where unnecessary modifications are made to a translation, diverging from the principle of minimal editing.
  • BhashaVerse : Translation Ecosystem for Indian Subcontinent Languages
    5 Dec 2024 0 repositories listed
    This paper focuses on developing translation models and related applications for 36 Indian languages, including Assamese, Awadhi, Bengali, Bhojpuri, Braj, Bodo, Dogri, English, Konkani, Gondi, Gujarati, Hindi, Hinglish…
  • Together We Can: Multilingual Automatic Post-Editing for Low-Resource Languages
    23 Oct 2024 0 repositories listed
    This exploratory study investigates the potential of multilingual Automatic Post-Editing (APE) systems to enhance the quality of machine translations for low-resource Indo-Aryan languages.
  • HW-TSC's Submission to the CCMT 2024 Machine Translation Tasks
    23 Sep 2024 0 repositories listed
    This paper presents the submission of Huawei Translation Services Center (HW-TSC) to machine translation tasks of the 20th China Conference on Machine Translation (CCMT 2024).
  • APE-then-QE: Correcting then Filtering Pseudo Parallel Corpora for MT Training Data Creation
    18 Dec 2023 0 repositories listed
  • Domain Terminology Integration into Machine Translation: Leveraging Large Language Models
    22 Oct 2023 0 repositories listed
  • TMU NMT System with Automatic Post-Editing by Multi-Source Levenshtein Transformer for the Restricted Translation Task of WAT 2022
    1 Oct 2022 0 repositories listed
  • PePe: Personalized Post-editing Model utilizing User-generated Post-edits
    21 Sep 2022 0 repositories listed
  • An Empirical Study of Automatic Post-Editing
    16 Sep 2022 0 repositories listed
  • Empirical Analysis of Noising Scheme based Synthetic Data Generation for Automatic Post-editing
    1 Jun 2022 0 repositories listed
  • Advancing Semi-Supervised Learning for Automatic Post-Editing: Data-Synthesis by Mask-Infilling with Erroneous Terms
    8 Apr 2022 0 repositories listed
  • A Self-Supervised Automatic Post-Editing Data Generation Tool
    24 Nov 2021 0 repositories listed
  • Adapting Neural Machine Translation for Automatic Post-Editing
    1 Nov 2021 0 repositories listed
  • Netmarble AI Center’s WMT21 Automatic Post-Editing Shared Task Submission
    1 Nov 2021 0 repositories listed
  • Netmarble AI Center's WMT21 Automatic Post-Editing Shared Task Submission
    14 Sep 2021 0 repositories listed
  • Interactive Models for Post-Editing
    1 Jul 2021 0 repositories listed
  • Building The First English-Brazilian Portuguese Corpus for Automatic Post-Editing
    1 Dec 2020 0 repositories listed
  • Alibaba’s Submission for the WMT 2020 APE Shared Task: Improving Automatic Post-Editing with Pre-trained Conditional Cross-Lingual BERT
    1 Nov 2020 0 repositories listed
  • Cross-Lingual Transformers for Neural Automatic Post-Editing
    1 Nov 2020 0 repositories listed
  • Findings of the WMT 2020 Shared Task on Automatic Post-Editing
    1 Nov 2020 0 repositories listed
  • HW-TSC’s Participation at WMT 2020 Automatic Post Editing Shared Task
    1 Nov 2020 0 repositories listed
  • Noising Scheme for Data Augmentation in Automatic Post-Editing
    1 Nov 2020 0 repositories listed
  • POSTECH-ETRI’s Submission to the WMT2020 APE Shared Task: Automatic Post-Editing with Cross-lingual Language Model
    1 Nov 2020 0 repositories listed
  • Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing
    19 Sep 2020 0 repositories listed
  • A Post-Editing Dataset in the Legal Domain: Do we Underestimate Neural Machine Translation Quality?
    1 May 2020 0 repositories listed
  • NMT and PBSMT Error Analyses in English to Brazilian Portuguese Automatic Translations
    1 May 2020 0 repositories listed
  • Automatic Post-Editing for Machine Translation
    18 Oct 2019 0 repositories listed
  • Improving CAT Tools in the Translation Workflow: New Approaches and Evaluation
    16 Aug 2019 0 repositories listed
  • The Transference Architecture for Automatic Post-Editing
    16 Aug 2019 0 repositories listed
  • Transformer-based Automatic Post-Editing with a Context-Aware Encoding Approach for Multi-Source Inputs
    15 Aug 2019 0 repositories listed
  • UdS Submission for the WMT 19 Automatic Post-Editing Task
    9 Aug 2019 0 repositories listed
  • APE through Neural and Statistical MT with Augmented Data. ADAPT/DCU Submission to the WMT 2019 APE Shared Task
    1 Aug 2019 0 repositories listed
  • Effort-Aware Neural Automatic Post-Editing
    1 Aug 2019 0 repositories listed
  • Findings of the WMT 2019 Shared Task on Automatic Post-Editing
    1 Aug 2019 0 repositories listed
  • Improving Translations by Combining Fuzzy-Match Repair with Automatic Post-Editing
    1 Aug 2019 0 repositories listed
  • Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder
    1 Aug 2019 0 repositories listed
  • USAAR-DFKI -- The Transference Architecture for English--German Automatic Post-Editing
    1 Aug 2019 0 repositories listed
  • Simple Automatic Post-editing for Arabic-Japanese Machine Translation
    14 Jul 2019 0 repositories listed
  • Unbabel's Submission to the WMT2019 APE Shared Task: BERT-based Encoder-Decoder for Automatic Post-Editing
    30 May 2019 0 repositories listed
  • APE at Scale and its Implications on MT Evaluation Biases
    9 Apr 2019 0 repositories listed
  • A Transformer-Based Multi-Source Automatic Post-Editing System
    1 Oct 2018 0 repositories listed
  • Alibaba Submission for WMT18 Quality Estimation Task
    1 Oct 2018 0 repositories listed
  • DFKI-MLT System Description for the WMT18 Automatic Post-editing Task
    1 Oct 2018 0 repositories listed
  • 1 Oct 2018 0 repositories listed
  • Findings of the WMT 2018 Shared Task on Automatic Post-Editing
    1 Oct 2018 0 repositories listed
  • Multi-encoder Transformer Network for Automatic Post-Editing
    1 Oct 2018 0 repositories listed
  • Multi-source transformer with combined losses for automatic post editing
    1 Oct 2018 0 repositories listed
  • MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing
    1 Sep 2018 0 repositories listed
  • 20 Mar 2018 0 repositories listed
  • A Comparison of Machine Translation Paradigms for Use in Black-Box Fuzzy-Match Repair
    1 Mar 2018 0 repositories listed
  • Are we experiencing the Golden Age of Automatic Post-Editing?
    1 Mar 2018 0 repositories listed
  • Automatic Post-Editing and Machine Translation Quality Estimation at eBay
    1 Mar 2018 0 repositories listed
  • Challenges in Adaptive Neural Machine Translation
    1 Mar 2018 0 repositories listed
  • Combining Quality Estimation and Automatic Post-editing to Enhance Machine Translation output
    1 Mar 2018 0 repositories listed
  • Fine-grained evaluation of Quality Estimation for Machine translation based on a linguistically motivated Test Suite
    1 Mar 2018 0 repositories listed
  • Lightweight Word-Level Confidence Estimation for Neural Interactive Translation Prediction
    1 Mar 2018 0 repositories listed
  • Machine translation at Booking.com: what's next?
    1 Mar 2018 0 repositories listed
  • Proceedings of the AMTA 2018 Workshop on Translation Quality Estimation and Automatic Post-Editing
    1 Mar 2018 0 repositories listed
  • Unbabel: How to combine AI with the crowd to scale professional-quality translation
    1 Mar 2018 0 repositories listed
  • Japanese to English/Chinese/Korean Datasets for Translation Quality Estimation and Automatic Post-Editing
    1 Nov 2017 0 repositories listed
  • CUNI System for WMT17 Automatic Post-Editing Task
    1 Sep 2017 0 repositories listed
  • Findings of the 2017 Conference on Machine Translation (WMT17)
    1 Sep 2017 0 repositories listed
  • Generating titles for millions of browse pages on an e-Commerce site
    1 Sep 2017 0 repositories listed
  • LIG-CRIStAL Submission for the WMT 2017 Automatic Post-Editing Task
    1 Sep 2017 0 repositories listed
  • Multi-source Neural Automatic Post-Editing: FBK's participation in the WMT 2017 APE shared task
    1 Sep 2017 0 repositories listed
  • Neural Post-Editing Based on Quality Estimation
    1 Sep 2017 0 repositories listed
  • The AMU-UEdin Submission to the WMT 2017 Shared Task on Automatic Post-Editing
    1 Sep 2017 0 repositories listed
  • Unbabel's Participation in the WMT17 Translation Quality Estimation Shared Task
    1 Sep 2017 0 repositories listed
  • LIG-CRIStAL System for the WMT17 Automatic Post-Editing Task
    17 Jul 2017 0 repositories listed
  • Attention Strategies for Multi-Source Sequence-to-Sequence Learning
    1 Jul 2017 0 repositories listed
  • An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing
    13 Jun 2017 0 repositories listed
  • Consistent Translation of Repeated Nouns using Syntactic and Semantic Cues
    1 Apr 2017 0 repositories listed
  • Neural Automatic Post-Editing Using Prior Alignment and Reranking
    1 Apr 2017 0 repositories listed
  • Online Automatic Post-editing for MT in a Multi-Domain Translation Environment
    1 Apr 2017 0 repositories listed

Syntology lines on 4 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections