539 research outputs found
Sort by
CUNI in WMT15: Chimera Strikes Again
No full textThis paper describes our WMT15 system submission for the translation task, a hybrid system for English-to-Czech translation. We repeat the successful setup from the previous two years
TeamUFAL: WSD+EL as Document Retrieval
No full textThis paper describes our system for SemEval-
2015 Task 13: Multilingual All-Words Sense
Disambiguation and Entity Linking. We have
participated with our system in the sub-task
which aims at monolingual all-words disambiguation
and entity linking. Aside from system
description, we pay closer attention to the
evaluation of system output
Results of the WMT15 Tuning Shared Task
Get PDFThis paper presents the results of the WMT15 Tuning Shared Task. We provided the
participants of this task with a complete machine translation system and asked them to tune its
internal parameters (feature weights). The tuned systems were used to translate the test set and
the outputs were manually ranked for translation quality. We received 4 submissions in the
English-Czech and 6 in the Czech-English translation direction. In addition, we ran
3 baseline setups, tuning the
parameters with standard optimizers for BLEU score
Translation Model Interpolation for Domain Adaptation in TectoMT
No full textWe present an implementation of domain adaptation by translation model interpolation in the
TectoMT translation system with deep transfer. We evaluate the method on six language pairs
with a 1000-sentence in-domain parallel corpus, and obtain improvements of up to 3 BLEU
points. The interpolation weights are set uniformly, without employing any tuning
New Language Pairs in TectoMT
Get PDFThe TectoMT tree-to-tree machine translation system has been updated this year to support easier retraining for more translation directions. We use multilingual standards for morphology and syntax annotation and language-independent base rules. We include a simple, non-parametric way of combining TectoMT’s transfer model outputs
Language technology for the medical domain
No full textThe talk presented activities in the area of language technology and specifically machine translation in the medical domain in the context of EC-funded projects
Depfix: Automatic Post-editing of SMT
No full textDepfix, an open-source system for automatic post-editing of phrase-based machine translation outputs. Depfix employs a range of natural language processing tools to obtain analyses of the input sentences, and uses a set of rules to correct common or serious errors in machine translation outputs
Findings of the 2015 Workshop on Statistical Machine Translation
Get PDFThis 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 translation quality,
and an automatic post-editing task. This
year, 68 machine translation systems from
24 institutions were submitted to the ten
translation directions in the standard translation
task. An additional 7 anonymized
systems were included, and were then
evaluated both automatically and manually.
The quality estimation task had three
subtasks, with a total of 10 teams, submitting
34 entries. The pilot automatic postediting
task had a total of 4 teams, submitting
7 entries
Giving a Sense: A Pilot Study in Concept Annotation from Multiple Resources
No full textWe present a pilot study in web-based annotation of words with senses coming
from several knowledge bases and sense inventories. The study is the first step in a
planned larger annotation of “grounding” and should allow us to select a subset of these
“dictionaries” that seem to cover any given text reasonably well and show an acceptable
level of inter-annotator agreement
Machine Translation of Natural Languages
No full textMachine Translation is as old as the field of Computational Linguistics itself. It is also a problem that has been predicted to „be solved in the next five years“ many times, but in fact it is not yet solved today. Machine translation has been naively considered a simple problem solvable by simple statistical means, then studied in depth by complicated but unsuccessful detailed sets of rules trying to describe all details of natural language use, only to return to statistical approach on a completely different level, using a combination of linguistic analysis and powerful machine learning algorithms