mlsanityData to 14 Oct 2026

MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing

arXiv 1809.00188 ↗First posted 1 Sep 2018cs.CLcited by 13

Not on the map. Why?

Abstract (arXiv)

This paper describes the Microsoft and University of Edinburgh submission to the Automatic Post-editing shared task at WMT2018. Based on training data and systems from the WMT2017 shared task, we re-implement our own models from the last shared task and introduce improvements based on extensive parameter sharing. Next we experiment with our implementation of dual-source transformer models and data selection for the IT domain. Our submissions decisively wins the SMT post-editing sub-task establishing the new state-of-the-art and is a very close second (or equal, 16.46 vs 16.50 TER) in the NMT sub-task. Based on the rather weak results in the NMT sub-task, we hypothesize that neural-on-neural APE might not be actually useful.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 4; 2023: 2; 2024: 0; 2025: 1; 2026: 1.

13 papers.

Sort:

  1. 2023Iterative Translation Refinement with Large Language Modelscited by 27
  2. 2021Focused Attention Improves Document-Grounded Generationcited by 24
  3. 2021WeTS: A Benchmark for Translation Suggestioncited by 8
  4. 2022Integrating Translation Memories into Non-Autoregressive Machine Translationcited by 5
  5. 2021Towards Personalised and Document-level Machine Translation of Dialoguecited by 4
  6. 2021Transfer Learning for Sequence Generation: from Single-source to Multi-sourcecited by 2
  7. 2022Bilingual Synchronization: Restoring Translational Relationships with Editing Operationscited by 2
  8. 2021Revisiting Context Choices for Context-aware Machine Translationcited by 1
  9. 2022PePe: Personalized Post-editing Model utilizing User-generated Post-editscited by 1
  10. 2023A Case Study on Context Encoding in Multi-Encoder based Document-Level Neural Machine Translationcited by 1
  11. 2022An Empirical Study of Automatic Post-Editingcited by 0
  12. 2025LangMark: A Multilingual Dataset for Automatic Post-Editingcited by 0
1 more
  1. 2026Confident but Wrong: A Constrained Decoding Diagnostic for Low-Resource Automatic Post-Editingcited by 0