Findings of the 2016 Conference on Machine Translation (2016-08-12T00:00:00.000000Z)

TL;DR

The results of the WMT16 shared tasks are presented, which included five machine translation (MT) tasks (standard news, IT-domain, biomedical, multimodal, pronoun), three evaluation tasks (metrics, tuning, run-time estimation of MT quality), and an automatic post-editing task and bilingual document alignment task.

Abstract

This paper presents the results of the WMT16 shared tasks, which included five machine translation (MT) tasks (standard news, IT-domain, biomedical, multimodal, pronoun), three evaluation tasks (metrics, tuning, run-time estimation of MT quality), and an automatic post-editing task and bilingual document alignment task. This year, 102 MT systems from 24 institutions (plus 36 anonymized online systems) were submitted to the 12 translation directions in the news translation task. The IT-domain task received 31 submissions from 12 institutions in 7 directions and the Biomedical task received 15 submissions systems from 5 institutions. Evaluation was both automatic and manual (relative ranking and 100-point scale assessments). The quality estimation task had three subtasks, with a total of 14 teams, submitting 39 entries. The automatic post-editing task had a total of 6 teams, submitting 11 entries.

Authors

B. Haddow

11 papers

Philipp Koehn

8 papers

Antonio Jimeno-Yepes

4 papers

TL;DR

Abstract

Authors

References142 items

Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction

Translation Quality Estimation using Recurrent Neural Network

CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered

Edinburgh’s Statistical Machine Translation Systems for WMT16

A Shared Task on Multimodal Machine Translation and Crosslingual Image Description

The QT21/HimL Combined Machine Translation System

The JHU Machine Translation Systems for WMT 2016

The AFRL-MITLL WMT16 News-Translation Task Systems

Hybrid Morphological Segmentation for Phrase-Based Machine Translation

LIMSI@WMT’16: Machine Translation of News

LIMSI’s Contribution to the WMT’16 Biomedical Translation Task

Results of the WMT16 Metrics Shared Task

NRC Russian-English Machine Translation System for WMT 2016

The TALP–UPC Spanish–English WMT Biomedical Task: Bilingual Embeddings and Char-based Neural Language Model Rescoring in a Phrase-based System

UGENT-LT3 SCATE Submission for WMT16 Shared Task on Quality Estimation

The UU Submission to the Machine Translation Quality Estimation Task

MetaMind Neural Machine Translation System for WMT 2016

The RWTH Aachen University English-Romanian Machine Translation System for WMT 2016

Abu-MaTran at WMT 2016 Translation Task: Deep Learning, Morphological Segmentation and Tuning on Character Sequences

DFKI’s system for WMT16 IT-domain task, including analysis of systematic errors

YSDA Participation in the WMT’16 Quality Estimation Shared Task

The Edinburgh/LMU Hierarchical Machine Translation System for WMT 2016

UAlacant word-level and phrase-level machine translation quality estimation systems at WMT 2016

SHEF-LIUM-NN: Sentence level Quality Estimation with Neural Network Features

IXA Biomedical Translation System at WMT16 Biomedical Translation Task

Findings of the WMT 2016 Bilingual Document Alignment Shared Task

USFD’s Phrase-level Quality Estimation Systems

TÜBİTAK SMT System Submission for WMT2016

Dictionary-based Domain Adaptation of MT Systems without Retraining

SimpleNets: Quality Estimation with Resource-Light Neural Networks

SHEF-MIME: Word-level Quality Estimation Using Imitation Learning

SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task

Merged bilingual trees based on Universal Dependencies in Machine Translation

English-Portuguese Biomedical Translation Task Using a Genuine Phrase-Based Statistical Machine Translation Approach

Yandex School of Data Analysis approach to English-Turkish translation at WMT16 News Translation Task

Phrase-Based SMT for Finnish with More Data, Better Models and Alternative Alignment and Translation Tools

Data Selection for IT Texts using Paragraph Vector

Metrics for Evaluation of Word-level Machine Translation Quality Estimation

Recurrent Neural Network based Translation Quality Estimation

Bilingual Embeddings and Word Alignments for Translation Quality Estimation

NYU-MILA Neural Machine Translation Systems for WMT’16

Results of the WMT16 Tuning Shared Task

Edinburgh Neural Machine Translation Systems for WMT 16

The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16

MultiVec: a Multilingual and Multilevel Representation Learning Toolkit for NLP

The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT

The Scielo Corpus: a Parallel Corpus of Scientific Publications for Biomedicine

Cohere: A Toolkit for Local Coherence

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

MARMOT: A Toolkit for Translation Quality Estimation at the Word Level

Referential translation machines for predicting semantic similarity

Can machine translation systems be evaluated by the crowd alone

QUality Estimation from ScraTCH (QUETCH): Deep Learning for Word-level Translation Quality Estimation

USAAR-SAPE: An English–Spanish Statistical Automatic Post-Editing System

USHEF and USAAR-USHEF participation in the WMT15 QE shared task

New Language Pairs in TectoMT

UAlacant word-level machine translation quality estimation system at WMT 2015

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

Findings of the 2015 Workshop on Statistical Machine Translation

Neural Machine Translation of Rare Words with Subword Units

Exploring the Planet of the APEs: a Comparative Study of State-of-the-art Methods for MT Automatic Post-Editing

Multi-level Translation Quality Prediction with QuEst++

Improving Evaluation of Machine Translation Quality Estimation

Searching for Context: a Study on Document-Level Labels for Translation Quality Estimation

Neural Machine Translation by Jointly Learning to Align and Translate

Latent Domain Translation Models in Mix-of-Domains Haystack

Introducing the SPMRL 2014 Shared Task on Parsing Morphologically-rich Languages

LIG System for Word Level QE task at WMT14

Efficient Elicitation of Annotations for Human Evaluation of Machine Translation

FBK-UPV-UEdin participation in the WMT14 Quality Estimation shared-task

Findings of the 2014 Workshop on Statistical Machine Translation

N-gram Counts and Language Models from the Common Crawl

Is Machine Translation Getting Better over Time?

Turning on the Turbo: Fast Third-Order Non-Projective Turbo Parsers

Continuous Measurement Scales in Human Evaluation of Machine Translation

FBK-UEdin Participation to the WMT13 Quality Estimation Shared Task