• Publications
  • Influence
Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search
TLDR
Experiments show that GBS can provide large improvements in translation quality in interactive scenarios, and that, even without any user input, it can be used to achieve significant gains in performance in domain adaptation scenarios. Expand
Findings of the 2015 Workshop on Statistical Machine Translation
This paper presents the results of the WMT15 shared tasks, which included a standard news translation task, a metrics task, a tuning task, a task for run-time estimation of machine translationExpand
Pushing the Limits of Translation Quality Estimation
TLDR
A new, carefully engineered, neural model is stacked into a rich feature-based word-level quality estimation system and the output of an automatic post-editing system is used as an extra feature, obtaining striking results on WMT16. Expand
Sense Clustering Using Wikipedia
TLDR
A novel method for generating a coarse-grained sense inventory from Wikipedia using a machine learning framework and multilingual features are shown to improve the clustering accuracy, especially for languages that are less comprehensive than English. Expand
Unbabel's Participation in the WMT16 Word-Level Translation Quality Estimation Shared Task
TLDR
The Unbabel team's two submitted systems are described: a feature-rich sequential linear model with syntactic features and a stacked combination of the linear system with three different deep neural networks, mixing feedforward, convolutional, and recurrent layers. Expand
The DCU Discourse Parser for Connective, Argument Identification and Explicit Sense Classification
TLDR
Focusing on achieving good performance when inferring explicit discourse relations, maximum entropy and recurrent neural networks are applied to different sub-tasks such as connective identification, argument extraction, and sense classification. Expand
Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models
TLDR
The lack of sufficient training data is identified as the major obstacle to training high-performing models, and a new state of the art in reconstruction of surface realizations from obfuscated text is presented. Expand
Evaluating the Supervised and Zero-shot Performance of Multi-lingual Translation Models
TLDR
An in-depth evaluation of the translation performance of different models, highlighting the trade-offs between methods of sharing decoder parameters, finds that models which have task-specificDecoder parameters outperform models where decoder parameter are fully shared across all tasks. Expand
Ensembling Factored Neural Machine Translation Models for Automatic Post-Editing and Quality Estimation
TLDR
This work presents a novel approach to Automatic Post-Editing (APE) and Word-Level Quality Estimation (QE) using ensembles of specialized Neural Machine Translation (NMT) systems, training a suite of NMT models that use different input representations, but share the same output space. Expand
MARMOT: A Toolkit for Translation Quality Estimation at the Word Level
TLDR
Marmot contains utilities targeted at quality estimation at the word and phrase level and can be used as a framework for extracting features and learning models for many common natural language processing tasks. Expand
...
1
2
3
...