• Publications
  • Influence
Findings of the 2017 Conference on Machine Translation (WMT17)
tl;dr
This paper presents the results of the WMT17 shared tasks, which included three machine translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and run-time estimation of MT quality), and a neural MT training task. Expand
  • 249
  • 20
  • Open Access
Findings of the 2015 Workshop on Statistical Machine Translation
tl;dr
We present the results of the shared tasks of the Workshop on Statistical Machine Translation (WMT) held at EMNLP 2015. Expand
  • 221
  • 14
  • Open Access
Is It the Right Answer? Exploiting Web Redundancy for Answer Validation
tl;dr
We present a novel approach to answer validation based on the intuition that the amount of implicit knowledge which connects an answer to a question can be quantitatively estimated by exploiting the redundancy of Web information. Expand
  • 187
  • 10
  • Open Access
MuST-C: a Multilingual Speech Translation Corpus
tl;dr
We created MuST-C, a multilingual speech translation corpus whose size and quality will facilitate the training of end-to-end systems for SLT from English into 8 languages. Expand
  • 64
  • 10
  • Open Access
Junction-aware extraction and regularization of urban road networks in high-resolution SAR images
tl;dr
A general processing framework for urban road network extraction in high-resolution SAR images is proposed. Expand
  • 104
  • 8
  • Open Access
An Open-Source Package for Recognizing Textual Entailment
tl;dr
This paper presents a general-purpose open source package for recognizing Textual Entailment. Expand
  • 55
  • 8
  • Open Access
I-CAB: the Italian Content Annotation Bank
tl;dr
In this paper we present work in progress for the c reation of the Italian Content Annotation Bank (I-C AB), a corpus of Italian news annotated with semantic information at different le vels. Expand
  • 67
  • 7
  • Open Access
eSCAPE: a Large-scale Synthetic Corpus for Automatic Post-Editing
Training models for the automatic correction of machine-translated text usually relies on data consisting of (source, MT, human post- edit) triplets providing, for each source sentence, examples ofExpand
  • 26
  • 6
  • Open Access
Towards Cross-Lingual Textual Entailment
tl;dr
This paper investigates cross-lingual textual entailment as a semantic relation between two text portions in different languages, and proposes a prospective research direction. Expand
  • 66
  • 5
  • Open Access
Semeval-2012 Task 8: Cross-lingual Textual Entailment for Content Synchronization
tl;dr
This paper presents the first round of the task on Cross-lingual Textual Entailment for Content Synchronization, organized within SemEval-2012. Expand
  • 53
  • 4