539 research outputs found
Sort by
Khresmoi Query Translation Test Data 2.0
No full textThis package contains data sets for development and testing of machine translation of medical search short queries between Czech, English, French, German, Hungarian, Polish, Spanish and Swedish. The queries come from general public and medical experts
Slavic Forest, Norwegian Wood (scripts)
No full textTools and scripts used to create the cross-lingual parsing models submitted to VarDial 2017 shared task (https://bitbucket.org/hy-crossNLP/vardial2017) and described in a paper by the same authors titled Slavic Forest, Norwegian Wood
CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
No full textThe Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets. In 2017, one of two tasks was devoted to learning dependency parsers for a large number of languages, in a real-world setting without any gold-standard annotation on input. All test sets followed a unified annotation scheme, namely that of Universal Dependencies. In this paper, we define the task and evaluation methodology, describe data preparation, report and analyze the main results, and provide a brief categorization of the different approaches of the participating systems
Slavic Forest, Norwegian Wood (models)
No full textTrained models for UDPipe used to produce our final submission to VarDial 2017 shared task (https://bitbucket.org/hy-crossNLP/vardial2017) and described in a paper by the same authors titled Slavic Forest, Norwegian Wood
CUNI Submission in WMT17: Chimera Goes Neural
No full textThis paper describes the neural and
phrase-based machine translation systems
submitted by CUNI to English-Czech
News Translation Task of WMT17. We
experiment with synthetic data for training
and try several system combination techniques,
both neural and phrase-based. Our
primary submission CU-CHIMERA ends
up being phrase-based backbone which incorporates
neural and deep-syntactic candidate
translations
Medical-domain Machine Translation in KConnect
No full textAchievements in Medical-domain Machine Translation within the KConnect projec
Khresmoi Summary Translation Test Data 2.0
No full textThis package contains data sets for development (Section dev) and testing (Section test) of machine translation of sentences from summaries of medical articles between Czech, English, French, German, Hungarian, Polish, Spanish
and Swedish. Version 2.0 extends the previous version by adding Hungarian, Polish, Spanish, and Swedish translations
Producing Unseen Morphological Variants in Statistical Machine Translation
No full textTranslating 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 advantage of context information from both the source language and the target language sides
CUNI Experiments for WMT17 Metrics Task
No full textIn this report paper we propose three different methods for automatic evaluation of the machine translation (MT) quality. Two of the metrics are trainable on direct-assessment scores and two of them use dependency structures. The trainable metric AutoDA, which uses deep-syntactic features, achieved better correlation with humans compared e.g. to the chrF3 metric
Results of the WMT17 Neural MT Training Task
No full textThis paper presents the results of the WMT17 Neural MT Training Task.
The objective of this task is to explore the methods of training a fixed neural architecture, aiming primarily at the best translation quality and, as a secondary goal, shorter training time.
Task participants were provided with a complete neural machine translation system, fixed training data and the configuration of the network.
The translation was performed in the English-to-Czech direction and the task was divided into two subtasks of different configurations - one scaled to fit on a 4GB and another on an 8GB GPU card.
We received 3 submissions for the 4GB variant and 1 submission for the 8GB variant; we provided also our run for each of the sizes and two baselines.
We translated the test set with the trained models and evaluated the outputs using several automatic metrics.
We also report results of the human evaluation of the submitted systems