MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing
| Autor: | Marcin Junczys-Dowmunt, Roman Grundkiewicz |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Training set Computer Science - Computation and Language Computer science business.industry computer.software_genre Dual source Artificial intelligence business computer Computation and Language (cs.CL) Data selection Natural language processing Transformer (machine learning model) |
| Zdroj: | WMT (shared task) |
| DOI: | 10.48550/arxiv.1809.00188 |
| Popis: | 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. Comment: Winning submissions for WMT2018 APE shared task |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|