539 research outputs found
Sort by
Two-Step Machine Translation with Lattices
No full textThe idea of two-step machine translation was introduced to divide the complexity of the search space into two independent steps: (1)
lexical translation and reordering, and (2) conjugation and declination in the target language. In this paper, we extend the two-step
machine translation structure by replacing state-of-the-art phrase-based machine translation with the hierarchical machine translation in
the 1st step. We further extend the fixed string-based input format of the 2nd step with word lattices (Dyer et al., 2008); this provides
the 2nd step with the opportunity to choose among a sample of possible reorderings instead of relying on the single best one as produced
by the 1st step
Cross-lingual Coreference Resolution of Pronouns
Get PDFThis work is, to our knowledge, a first attempt at a machine learning approach to cross-lingual
coreference resolution, i.e. coreference resolution (CR) performed on a bitext. Focusing on CR of English pronouns, we leverage language differences and enrich the feature set of a standard monolingual CR system for English with features extracted from the Czech side of the bitext. Our work also includes a supervised pronoun aligner that outperforms a GIZA++ baseline in terms of both intrinsic evaluation and evaluation on CR. The final cross-lingual CR system has successfully outperformed both a monolingual CR and a cross-lingual projection system
Multilingual Aspects of the Khresmoi project
No full textEvropský projekt Khresmoi vyvíjí multilinguální a multimodální vyhledávací systém v oboru biomedicíny
Japonsko-český strojový překlad
No full textThe article describes a prototype of Japanese-Czech machine translation system based on deep syntactic analysis. A required preparation step includes the collection and processing of parallel data. We circumvent the lack of directly parallel data by machine-translating the English side of our collection of Japanese-English data into Czech
Depfix, Automatic Post-editing of SMT
No full textDepfix is 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. Depfix is currently implemented only for English-to-Czech translation direction
A Tagged Corpus and a Tagger for Urdu
No full textIn this paper, we describe a release of a sizeable monolingual Urdu corpus automatically tagged with part-of-speech tags.
We extend the work of Jawaid and Bojar (2012) who use three different taggers and then apply a voting scheme to
disambiguate among the different choices suggested by each tagger. We run this complex ensemble on a large monolingual
corpus and release the tagged corpus. Additionally, we use this data to train a single standalone tagger which will
hopefully significantly simplify Urdu processing. The standalone tagger obtains the accuracy of 88.74% on test data
ShARe/CLEF eHealth Evaluation Lab 2014, Task 3: User-centred health information retrieval
No full textThis paper presents the results of task 3 of the ShARe/CLEF eHealth Evaluation Lab 2014 focused on user-centred health information retrieval
Khresmoi Query Translation Test Data 1.0
No full textThis package contains data sets for development and testing of machine translation of medical search short queries between Czech, English, French, and German. The queries come from general public and medical experts
Depfix Manual
No full textThe manual gives instructions on installing and running Depfix, our open-source tool for automatic post-editing of machine translation. We cover the steps required to use Depfix to process your own data. The manual also contains a description of the Depfix pipeline, including instructions that will enable you to modify the operation of Depfix
Integrating a Discriminative Classifier into Phrase-based and Hierarchical Decoding
Get PDFCurrent state-of-the-art statistical machine translation (SMT) relies
on simple feature functions which make independence assumptions at the
level of phrases or CFG rules. However, it is well-known that
discriminative models can benefit from rich features extracted from
the source sentence context outside of the applied phrase or CFG rule,
which is available at decoding time. We present a framework for the
open-source decoder Moses that allows discriminative models over
source context to easily be trained on a large number of examples and
then be included as feature functions in decoding