We provide a few insights on data selection for machine translation. We evaluate the quality of the new CzEng 1.0, a parallel data source used in WMT12. We describe a simple technique for reducing out-of-vocabulary rate after phrase extraction. We discuss the benefits of tuning towards multiple reference translations for English-Czech language pair. We introduce a novel approach to data selection by full-text indexing and search: we select sentences similar to th...

A summary of the development of neural MT at Charles University.

In this paper, we investigate the CoNLL Shared Task format, its properties and possibility of its use for complex annotations. We argue that, perhaps despite the original intent, it is one of the most important current formats for syntactically annotated data. We show the limits of the CoNLL-ST data format in its current form and propose several simple enhancements that push those limits further and make the format more robust and future proof. We analyse several different linguistic ...

The aim of this paper is to introduce Reductor, a program that automatically removes unused parts of the source code of valid programs written in the Mercury language. Reductor implements two main kinds of reductions: statical reduction and dynamical reduction. In the statical reduction, Reductor exploits semantic analysis of the Melbourne Mercury Compiler to nd routines which can be removed from the program. Dynamical reduction of routines additionally uses Mercury Deep Profiler and some ...

Following upon the last year's CUNI system for automatic post-editing of machine translation output, we focus on exploiting the potential of sequence-to-sequence neural models for this task. In this system description paper, we compare several encoder-decoder architectures on a smaller-scale models and present the system we submitted to WMT 2017 Automatic Post-Editing shared task based on this preliminary comparison. We also show how simple inclusion of synthetic data can improve the overa...

Maximum Entropy Principle has been used successfully in various NLP tasks. In this paper we propose a forward translation model consisting of a set of maximum entropy classifiers: a separate classifier is trained for each (sufficiently frequent) source-side lemma. In this way the estimates of translation probabilities can be sensitive to a large number of features derived from the source sentence (including non-local features, features making use of sentence s...

We introduce a taxonomy of factored phrase based translation scenarios and conduct a range of experiments in this taxonomy. We point out several common pitfalls when designing factored setups. The paper also describes our WMT12 submissions CU-BOJAR and CU-POOR-COMB.

Translating into morphologically rich languages is difficult. Although the coverage of lemmas may be reasonable, many morphological variants cannot be learned from the training data. We present a statistical translation system that is able to produce these inflected word forms. Different from most previous work, we do not separate morphological prediction from lexical choice into two consecutive steps. Our approach is novel in that it is integrated in decoding and takes advanta...

A summary of research activities in the area of machine translation in the EU (Technologies – Demands – Gaps – Roadmaps) has been presented, including contributions from multiple other EU-funded projects.

A summary of ten years of automatic MT evaluation, highlighting past successful metrics, current evaluation challenges and topics that need to be tackled in the future.