539 research outputs found
Sort by
CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered
No full textWe present a new release of the Czech-English parallel corpus CzEng. CzEng 1.6 consists of about 0.5 billion words (“gigaword”) in each language. The corpus is equipped with automatic annotation at a deep syntactic level of representation and alternatively in Universal Dependencies. Additionally, we release the complete annotation pipeline as a virtual machine in the Docker virtualization toolkit
Target-Side Context for Discriminative Models in Statistical Machine Translation
Get PDFDiscriminative translation models utilizing source context have been shown to help statistical machine translation performance. We propose a novel extension of this work using target context information. Surprisingly, we show that this model can be efficiently integrated directly in the decoding process. Our approach scales to large training data sizes and results in consistent improvements in translation quality on four language pairs. We also provide an analysis comparing the strengths of the baseline source-context model with our extended source-context and target-context model and we show that our extension allows us to better capture morphological coherence. Our work is freely available as part of Moses
If You Even Don't Have a Bit of Bible: Learning Delexicalized POS Taggers
No full textPart-of-speech (POS) tagging is sometimes considered an almost solved problem in NLP. Standard supervised approaches often reach accuracy above 95% if sufficiently large hand-labeled training data are available (typically several hundred thousand tokens or more). However, we still believe that it makes sense to study semi-supervised and unsupervised approaches
Deeper Machine Translation and Evaluation for German
No full textThis paper describes a hybrid Machine Translation (MT) system built for translating from English
to German in the domain of technical documentation. The system is based on three different
MT engines (phrase-based SMT, RBMT, neural) that are joined by a selection mechanism
that uses deep linguistic features within a machine learning process. It also presents a detailed
source-driven manual error analysis we have performed using a dedicated “test suite” that contains
selected examples of relevant phenomena. While automatic scores show huge differences
between the engines, the overall average number or errors they (do not) make is very similar for
all systems. However, the detailed error breakdown shows that the systems behave very differently
concerning the various phenomena
Results of the WMT16 Metrics Shared Task
Get PDFThis paper presents the results of the
WMT16 Metrics Shared Task. We asked
participants of this task to score the outputs
of the MT systems involved in the
WMT16 Shared Translation Task. We
collected scores of 16 metrics from 9 research
groups. In addition to that, we computed
scores of 9 standard metrics (BLEU,
SentBLEU, NIST, WER, PER, TER and
CDER) as baselines. The collected scores
were evaluated in terms of system-level
correlation (how well each metric’s scores
correlate with WMT16 official manual
ranking of systems) and in terms of segment
level correlation (how often a metric
agrees with humans in comparing two
translations of a particular sentence).
This year there are several additions to
the setup: large number of language pairs
(18 in total), datasets from different domains
(news, IT and medical), and different
kinds of judgments: relative ranking
(RR), direct assessment (DA) and HUME
manual semantic judgments. Finally, generation
of large number of hybrid systems
was trialed for provision of more conclusive
system-level metric rankings
Bilingual Embeddings and Word Alignments for Translation Quality Estimation
Get PDFThis paper describes our submission
UFAL MULTIVEC to the WMT16 Quality
Estimation Shared Task, for EnglishGerman
sentence-level post-editing effort
prediction and ranking. Our approach exploits
the power of bilingual distributed
representations, word alignments and also
manual post-edits to boost the performance
of the baseline QuEst++ set of
features. Our model outperforms the
baseline, as well as the winning system
in WMT15, Referential Translation Machines
(RTM), in both scoring and ranking
sub-tasks
A Framework for Discriminative Rule Selection in Hierarchical Moses
No full textWe propose two contributions to discriminative rule selection in hierarchical machine translation. First, we test previous approaches on two French-English translation tasks in domains for which only limited resources are available and show that they fail to improve translation quality. To improve on such tasks, we propose a rule selection model that is (i) global with rich label-dependent features (ii) trained with all available negative samples. Our global model yields significant improvements, up to 1 BLEU point, over previously proposed rule selection models
Using Term Position Similarity and Language Modeling for Bilingual Document Alignment
Get PDFThe WMT Bilingual Document Alignment
Task requires systems to assign
source pages to their “translations”, in a
big space of possible pairs. We present
four methods: The first one uses the term
position similarity between candidate document
pairs. The second method requires
automatically translated versions of the
target text, and matches them with the candidates.
The third and fourth methods try
to overcome some of the challenges presented
by the nature of the corpus, by
considering the string similarity of source
URL and candidate URL, and combining
the first two approaches
CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks
Get PDFNeural sequence to sequence learning recently became a very promising paradigm in machine translation, achieving competitive results with statistical phrase-based systems. In this system description paper, we attempt to utilize several recently published methods used for neural sequential learning in order to build systems for WMT 2016 shared tasks of Automatic Post-Editing and Multimodal Machine Translation
UFAL Submissions to the IWSLT 2016 MT Track
No full textWe present our submissions to the IWSLT 2016 machine
translation task, as our first attempt to translate subtitles and
one of our early experiments with neural machine translation
(NMT). We focus primarily on English→Czech translation
direction but perform also basic adaptation experiments for
NMT with German and also the reverse direction. Three MT
systems are tested: (1) our Chimera, a tight combination of
phrase-based MT and deep linguistic processing, (2) Neural
Monkey, our implementation of a NMT system in TensorFlow
and (3) Nematus, an established NMT system