539 research outputs found
Sort by
Enriching Source for English-to-Urdu Machine Translation
No full textThis paper focuses on the generation of case markers for free word order languages that use case markers as phrasal clitics for marking the relationship between the dependent- noun and its head. The generation of such clitics becomes essential task especially when translating from fixed word order languages where syntactic relations are identified by the positions of the dependent-nouns. To address the problem of missing markers on source-side, artificial markers are added in source to improve alignments with its target counterparts. Up to 1 BLEU point increase is observed over the baseline on different test sets for English-to-Urdu
SubGram: Extending Skip-gram Word Representation with Substrings
No full textSkip-gram (word2vec) is a recent method for creating vector representations of words (“distributed word representations”) using a neural network. The representation gained popularity in various areas of natural language processing, because it seems to capture syntactic and semantic information about words without any explicit supervision in this respect.
We propose SubGram, a refinement of the Skip-gram model to consider also the word structure during the training process, achieving large gains on the Skip-gram original test set
Prague Czech-English Dependency Treebank 2.0 Coref
No full textWe present an extended version of the Prague Czech-English Dependency Treebank 2.0 (PCEDT 2.0). It includes all annotation of coreference (the original one from PCEDT 2.0 as well as the new one) and improved cross-lingual alignment of coreferential expressions. The corpus released as PCEDT 2.0 Coref is publicly available
Findings of the 2016 Conference on Machine Translation (WMT16)
Get PDFThis paper presents the results of the
WMT16 shared tasks, which included five
machine translation (MT) tasks (standard
news, IT-domain, biomedical, multimodal,
pronoun), three evaluation tasks (metrics,
tuning, run-time estimation of MT quality),
and an automatic post-editing task
and bilingual document alignment task.
This year, 102 MT systems from 24 institutions
(plus 36 anonymized online systems)
were submitted to the 12 translation
directions in the news translation task. The
IT-domain task received 31 submissions
from 12 institutions in 7 directions and the
Biomedical task received 15 submissions
systems from 5 institutions. Evaluation
was both automatic and manual (relative
ranking and 100-point scale assessments)
CUNI-LMU Submissions in WMT2016: Chimera Constrained and Beaten
No full textThis paper describes the phrase-based systems
jointly submitted by CUNI and LMU
to English-Czech and English-Romanian
News translation tasks of WMT16. In contrast
to previous years, we strictly limited
our training data to the constraint datasets,
to allow for a reliable comparison with
other research systems. We experiment
with using several additional models in our
system, including a feature-rich discriminative
model of phrasal translation
SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task
Get PDFThis paper presents the description of 12
systems submitted to the WMT16 IT-task,
covering six different languages, namely
Basque, Bulgarian, Dutch, Czech, Portuguese
and Spanish. All these systems
were developed under the scope of the
QTLeap project, presenting a common
strategy. For each language two different
systems were submitted, namely a phrase-based
MT system built using Moses, and
a system exploiting deep language engineering
approaches, that in all the languages
but Bulgarian was implemented
using TectoMT. For 4 of the 6 languages,
the TectoMT-based system performs better
than the Moses-based one
Verb Sense Disambiguation in Machine Translation
No full textWe describe experiments in Machine Translation using word sense disambiguation (WSD) information. This work focuses on WSD in verbs, based on two different approaches -- verbal patterns based on corpus pattern analysis and verbal word senses from valency frames. We evaluate several options of using verb senses in the source-language sentences as an additional factor for the Moses statistical machine translation system.
Our results show a statistically significant translation quality improvement in terms of the BLEU metric for the valency frames approach, but in manual evaluation, both WSD methods bring improvements
Ten Years of WMT Evaluation Campaigns: Lessons Learnt
No full textThe WMT evaluation campaign (http://www.statmt.org/wmt16) has been run annually since 2006. It is a collection of shared
tasks related to machine translation, in which researchers compare their techniques against those of others in the field. The longest
running task in the campaign is the translation task, where participants translate a common test set with their MT systems. In addition
to the translation task, we have also included shared tasks on evaluation: both on automatic metrics (since 2008), which compare the
reference to the MT system output, and on quality estimation (since 2012), where system output is evaluated without a reference. An
important component of WMT has always been the manual evaluation, wherein human annotators are used to produce the official ranking
of the systems in each translation task. This reflects the belief of theWMTorganizers that human judgement should be the ultimate arbiter
of MT quality. Over the years, we have experimented with different methods of improving the reliability, efficiency and discriminatory
power of these judgements. In this paper we report on our experiences in running this evaluation campaign, the current state of the art in
MT evaluation (both human and automatic), and our plans for future editions of WMT
Particle Swarm Optimization Submission for WMT16 Tuning Task
Get PDFThis paper describes our submission to the
Tuning Task of WMT16. We replace the
grid search implemented as part of standard
minimum-error rate training (MERT)
in the Moses toolkit with a search based
on particle swarm optimization (PSO). An
older variant of PSO has been previously
successfully applied and we now test it
in optimizing the Tuning Task model for
English-to-Czech translation. We also
adapt the method in some aspects to allow
for even easier parallelization of the
search
Manual and Automatic Paraphrases for MT Evaluation
No full textParaphrasing of reference translations has been shown to improve the correlation with human judgements in automatic evaluation of
machine translation (MT) outputs. In this work, we present a new dataset for evaluating English-Czech translation based on automatic
paraphrases. We compare this dataset with an existing set of manually created paraphrases and find that even automatic paraphrases can
improve MT evaluation. We have also propose and evaluate several criteria for selecting suitable reference translations from a larger set