Findings of the Third Shared Task on Multimodal Machine Translation (2018-10-31T00:00:00.000000Z)

TL;DR

Compared to last year, the performance of the multimodal submissions improved, but text-only systems remain competitive.

Abstract

We present the results from the third shared task on multimodal machine translation. In this task a source sentence in English is supplemented by an image and participating systems are required to generate a translation for such a sentence into German, French or Czech. The image can be used in addition to (or instead of) the source sentence. This year the task was extended with a third target language (Czech) and a new test set. In addition, a variant of this task was introduced with its own test set where the source sentence is given in multiple languages: English, French and German, and participating systems are required to generate a translation in Czech. Seven teams submitted 45 different systems to the two variants of the task. Compared to last year, the performance of the multimodal submissions improved, but text-only systems remain competitive.

Authors

Loïc Barrault

10 papers

Lucia Specia

13 papers

Desmond Elliott

8 papers

TL;DR

Abstract

Authors

References43 items

CUNI System for the WMT18 Multimodal Translation Task

UMONS Submission for WMT18 Multimodal Translation Task

Sheffield Submissions for WMT18 Multimodal Translation Shared Task

LIUM-CVC Submissions for WMT18 Multimodal Translation Task

Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report

The MeMAD Submission to the WMT18 Multimodal Translation Task

Multimodal Lexical Translation

Marian: Fast Neural Machine Translation in C++

Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description

Neural Sequence Learning Models for Word Sense Disambiguation

Attention is All you Need

NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems

Imagination Improves Multimodal Translation

Self-Critical Sequence Training for Image Captioning

Multimodal Attention for Neural Machine Translation

A Shared Task on Multimodal Machine Translation and Crosslingual Image Description

Unsupervised Compound Splitting With Distributional Semantics Rivals Supervised Methods

Multi30K: Multilingual English-German Image Descriptions

OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles

Semi-supervised Word Sense Disambiguation with Neural Models

Multimodal Pivots for Image Caption Translation

Deep Residual Learning for Image Recognition

Multi-Language Image Description with Neural Sequence Models

Multilingual Image Description with Neural Sequence Models

Can machine translation systems be evaluated by the crowd alone

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

Neural Machine Translation by Jointly Learning to Align and Translate

Meteor Universal: Language Specific Translation Evaluation for Any Target Language

Open-Source Tools for Morphology, Lemmatization, POS Tagging and Named Entity Recognition

Microsoft COCO: Common Objects in Context

From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions

A Simple, Fast, and Effective Reparameterization of IBM Model 2

Appraise: an Open-Source Toolkit for Manual Evaluation of MT Output

Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability

Moses: Open Source Toolkit for Statistical Machine Translation

Bleu: a Method for Automatic Evaluation of Machine Translation

The AFRL-Ohio State WMT18 Multimodal System: Combining Visual with Traditional

Detectron

Piotr Dollár, and Kaiming He

A Study of Translation Edit Rate with Targeted Human Annotation

A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION

ii) Almost all systems achieved better results compared to the baseline text-only translation system

iii) Automatic metrics and human evaluation provided similar results

Field of Study

Venue Information

Name

Type

URL

Alternate Names