539 research outputs found
Sort by
B2SHARE: An Open eScience Data Sharing Platform
No full textScientific data sharing is becoming an essential service for data driven science and can significantly improve the scientific process by making reliable, and trustworthy data available. Thereby reducing redundant work, and providing insights on related research and recent advancements. For data sharing services to be useful in the scientific process, they need to fulfill a number of requirements that cover not only discovery, and access to data. But to ensure the integrity, and reliability of published data as well. B2SHARE, developed by the EUDAT project, provides such a data sharing service to scientific communities. For communities that wish to download, install and maintain their own service, it is also available as software. B2SHARE is developed with a focus on user-friendliness, reliability, and trustworthiness, and can be customized for different organizations and use-cases. In this paper we discuss the design, architecture, and implementation of B2SHARE. We show its usefulness in the scientific process with some case studies in the biodiversity field
Multi-source Cross-lingual Delexicalized Parser Transfer: Prague or Stanford?
No full textWe compare two annotation styles, Prague dependencies and Universal
Stanford Dependencies, in their adequacy for parsing.
We specifically focus on comparing the adposition attachment style, used in these two
formalisms, applied in multi-source cross-lingual delexicalized dependency
parser transfer performed by parse tree combination.
We show that in our setting, converting the adposition annotation to Stanford style in the
Prague style training treebanks leads to promising results.
We find that best results can be obtained by parsing the target sentences
with parsers trained on treebanks using both of the adposition annotation
styles in parallel,
and combining all the resulting parse trees together
after having converted them to the Stanford adposition style (+0.39% UAS over Prague
style baseline).
The score improvements are considerably more significant when using a smaller set of diverse source
treebanks (up to +2.24% UAS over the baseline)
Machine translation
No full textThe chapter on Machine translation in Oxford Handbook of Inflection starts by describing the few key approaches to machine translation and proceeds over individual stages of the process, highlighting the problems caused by the richness of word forms
Correspondences between Czech and English Coreferential Expressions
Get PDFV této práci představujeme podrobný srovnávací výzkum některých typů koreferenčních vztahů v češtině a angličtině na paralelním česko-anglickém korpusu. Zaměřujeme se na centrální, vztažná a anaforická zájmena. Vypracovali jsme algoritmus vylepšení automatického vyrovnání několika typů českých a anglických zájmen, který vylepšuje kvalitu vyrovnání nejen pro tyto typy ale a pro všechny ostatní. Korespondence daných typů zájmen byly anatovány ručně a dále lingvisticky analyzovány
MT-ComparEval
No full textMT-ComparEval is a tool for Machine Translation developers, which allows to compare and evaluate different MT systems (and their versions). MT-ComparEval includes several automatic MT evaluation metrics
Domain adaptation of statistical machine translation with domain-focused web crawling
No full textIn this paper, we tackle the problem of domain adaptation of statistical machine
translation (SMT) by exploiting domain-specific data acquired by domain-focused crawling
of text from the World Wide Web. We design and empirically evaluate a procedure for auto-
matic acquisition of monolingual and parallel text and their exploitation for system training,
tuning, and testing in a phrase-based SMT framework. We present a strategy for using such
resources depending on their availability and quantity supported by results of a large-scale
evaluation carried out for the domains of environment and labour legislation, two language
pairs (English–French and English–Greek) and in both directions: into and from English.
In general, MT systems trained and tuned on a general domain perform poorly on specific
domains and we show that such systems can be adapted successfully by retuning model
parameters using small amounts of parallel in-domain data, and may be further improved
by using additional monolingual and parallel training data for adaptation of language and
translation models. The average observed improvement in BLEU achieved is substantial at
15.30 points absolute
What a Transfer-Based System Brings to the Combination with PBMT
No full textWe present a thorough analysis of a combination of a statistical and a transfer-based system for English->Czech translation, Moses and TectoMT. We describe several techniques for inspecting such a system combination which are based both on automatic and manual evaluation. While TectoMT often produces bad translations, Moses is still able to select the good parts of them. In many cases, TectoMT provides useful novel translations which are otherwise simply unavailable to the statistical component, despite the very large training data. Our analyses confirm the expected behaviour that TectoMT helps with preserving grammatical agreements and valency requirements, but that it also improves a very diverse set of other phenomena. Interestingly, including the outputs of the
transfer-based system in the phrase-based search seems to have a positive effect on the search space. Overall, we find that the components of this combination are complementary and the final system produces significantly better translations than either component by itself
HindEnCorp – Hindi-English and Hindi-only Corpus for Machine Translation
Get PDFWe present HindEnCorp, a parallel corpus of Hindi and English, and HindMonoCorp, a monolingual corpus of Hindi in their release version 0.5. Both corpora were collected from web sources and preprocessed primarily for the training of statistical machine translation systems. HindEnCorp consists of 274k parallel sentences (3.9 million Hindi and 3.8 million English tokens). HindMonoCorp amounts to 787 million tokens in 44 million sentences. Both the corpora are freely available for non-commercial research and their preliminary release has been used by numerous participants of the WMT 2014 shared translation task
Lingua::Interset 2.026
No full textLingua::Interset is a universal morphosyntactic feature set to which all tagsets of all corpora/languages can be mapped. Version 2.026 covers 64 different tagsets of 37 languages
Dealing with Function Words in Unsupervised Dependency Parsing
No full textIn this paper, we show some properties of function words in dependency trees. Function
words are grammatical words, such as articles, prepositions, pronouns, conjunctions, or auxiliary verbs. These words are often short and very frequent in texts and therefore many of them can be easily recognized. We formulate a hypothesis that function words tend to have a fixed number of dependents and we prove this hypothesis on treebanks. Using this hypothesis, we are able to improve unsupervised dependency parsing and outperform previously published state-of-the-art results for many languages