The FBK Participation in the WMT15 Automatic Post-editing Shared Task

In this paper, we describe the “FBK EnglishSpanish Automatic Post-editing (APE)” systems submitted to the APE shared task at the WMT 2015. We explore the most widely used statistical APE technique (monolingual) and its most significant variant (context-aware). In this exploration, we introduce some novel task-specific dense features through which we observe improvements over the default setup of these approaches. We show these features are useful to prune the phrase table in order to remove unreliable rules and help the decoder to select useful translation options during decoding. Our primary APE system submitted at this shared task performs significantly better than the standard APE baseline.

• Publication year

  2015

• Venue

  WMT@EMNLP

• Publication date

  2015-09-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/W15-3025
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Online Multitask Learning for Machine Translation Quality Estimation

  2015cited by this paper
• Exploring the Planet of the APEs: a Comparative Study of State-of-the-art Methods for MT Automatic Post-Editing

  2015cited by this paper
• The AMU System in the CoNLL-2014 Shared Task: Grammatical Error Correction by Data-Intensive and Feature-Rich Statistical Machine Translation

  2014cited by this paper
• FBK-UPV-UEdin participation in the WMT14 Quality Estimation shared-task

  2014cited by this paper
• Adaptive Quality Estimation for Machine Translation

  2014cited by this paper
• Decoding with Large-Scale Neural Language Models Improves Translation

  2013cited by this paper
• FBK-UEdin Participation to the WMT13 Quality Estimation Shared Task

  2013cited by this paper
• QuEst - A translation quality estimation framework

  2013cited by this paper
• Match without a Referee: Evaluating MT Adequacy without Reference Translations

  2012cited by this paper
• Can Automatic Post-Editing Make MT More Meaningful

  2012cited by this paper
• KenLM: Faster and Smaller Language Model Queries

  2011cited by this paper
• Scikit-learn: Machine Learning in Python

  2011cited by this paper
• Statistical Post-Editing for a Statistical MT System

  2011cited by this paper
• IRSTLM: an open source toolkit for handling large scale language models

  2008cited by this paper
• Parallel Implementations of Word Alignment Tool

  2008cited by this paper
• Factored Translation Models

  2007cited by this paper
• Statistical Phrase-Based Post-Editing

  2007influential reference
• Improving Translation Quality by Discarding Most of the Phrasetable

  2007cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper
• A Study of Translation Edit Rate with Targeted Human Annotation

  2006cited by this paper
• Extremely randomized trees

  2006cited by this paper
• A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION

  2005cited by this paper
• Minimum Error Rate Training in Statistical Machine Translation

  2003cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• Improvements in Part-of-Speech Tagging with an Application to German

  1999cited by this paper

• Improving Neural Machine Translation with Soft Template Prediction

  2020cites this paper
• Factored Phrase-based Statistical Machine Pre-training with Extended Transformers

  2020cites this paper
• Building The First English-Brazilian Portuguese Corpus for Automatic Post-Editing

  2020cites this paper
• A review of the state-of-the-art in automatic post-editing

  2020influential citation
• Learning Non-Monotonic Automatic Post-Editing of Translations from Human Orderings

  2020cites this paper
• Simple Automatic Post-editing for Arabic-Japanese Machine Translation

  2019cites this paper
• Think Again Networks and the Delta Loss

  2019cites this paper
• Automatic Post-Editing for Machine Translation

  2019influential citation
• Improving Translations by Combining Fuzzy-Match Repair with Automatic Post-Editing

  2019cites this paper
• Automatic Post-Editing across Domains

  2019influential citation
• Multi-source transformer with combined losses for automatic post editing

  2018cites this paper
• Proceedings of the 21st Annual Conference of the European Association for Machine Translation

  2018cites this paper
• Quality expectations of machine translation

  2018cites this paper
• A Hybrid Machine Translation Framework for an Improved Translation Workflow

  2018cites this paper
• Combining Quality Estimation and Automatic Post-editing to Enhance Machine Translation output

  2018influential citation
• Adaptive Multi-pass Decoder for Neural Machine Translation

  2018influential citation
• Letting a Neural Network Decide Which Machine Translation System to Use for Black-Box Fuzzy-Match Repair

  2018cites this paper
• Guiding Neural Machine Translation Decoding with External Knowledge

  2017cites this paper
• Online Automatic Post-editing for MT in a Multi-Domain Translation Environment

  2017influential citation
• LIG-CRIStAL Submission for the WMT 2017 Automatic Post-Editing Task

  2017cites this paper
• Findings of the 2017 Conference on Machine Translation (WMT17)

  2017cites this paper
• Neural Post-Editing Based on Quality Estimation

  2017cites this paper
• Deliberation Networks: Sequence Generation Beyond One-Pass Decoding

  2017cites this paper
• LIG-CRIStAL System for the WMT17 Automatic Post-Editing Task

  2017cites this paper
• Multi-source Neural Automatic Post-Editing: FBK’s participation in the WMT 2017 APE shared task

  2017cites this paper
• The FBK Participation in the WMT 2016 Automatic Post-editing Shared Task

  2016influential citation
• Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing

  2016cites this paper
• Online Automatic Post-Editing across Domains

  2016influential citation
• Findings of the 2016 Conference on Machine Translation

  2016cites this paper
• Instance Selection for Online Automatic Post-Editing in a multi-domain scenario

  2016cites this paper
• English to Irish Machine Translation with Automatic Post-Editing

  2016cites this paper
• Findings of the 2015 Workshop on Statistical Machine Translation

  2015cites this paper