539 research outputs found
Sort by
Počítače asi nikdy nahradí lidského korektora ani překladatele
No full textAn interview for Radio Czech describing various approaches to machine translation and the difficulties with handling natural languages in general
MTMonkey: A Scalable Infrastructure for a Machine Translation Web Service
Get PDFWe present a web service which handles and distributes JSON-encoded HTTP
requests for machine translation (MT) among multiple machines running
an MT system, including text pre- and post processing.
It is currently used to provide MT between several languages
for cross-lingual information retrieval in the Khresmoi project.
The software consists of an application server and remote workers which handle
text processing and communicate translation requests to MT
systems. The communication between the application server and the workers is
based on the XML-RPC protocol. We present
the overall design of the software and test results which document
speed and scalability of our solution.
Our software is licensed under the Apache 2.0 licence and is available for
download from the Lindat-Clarin repository and Github
Khresmoi Professional: Multilingual Semantic Search for Medical Professionals
No full textThere is increasing interest in and need for innovative solutions to medical search. In this paper we present the EU-funded Khresmoi medical search and access system, currently in year 3 of 4 of development across 12 partners. The Khresmoi system uses a component-based architecture housed in the cloud to allow for the development of several innovative applications to support target users' medical information needs. The Khresmoi search systems based on this architecture have been designed to support the multilingual and multimodal information needs of three target groups: the general public, general practitioners and consultant radiologists. In this paper we focus on the presentation of the systems to support the latter two groups using semantic, multilingual text and image-based (including 2D and 3D radiology images) search
WMT Dependency Annotations 0.1
No full textWMT annotations are described in the paper Improvements to Syntax-based Machine Translation using Ensemble Dependency Parsers presented at The Second Workshop on Hybrid Approaches to Translation (HyTra) at ACL 2013. The annotations are done on the analytically layer of the Czech to English Data set from the Workshop on Machine Translation 2012 data.
The main purpose of this data set is to give researchers gold level dependency annotations for a data set that contains a gold level translations. This should allow researchers to analyze dependency annotations effect on machine translation
EnTam: An English-Tamil Parallel Corpus
No full textWe have collected English-Tamil bilingual data from some of the publicly available websites for NLP research involving Tamil. The standard set of processing has been applied on the the raw web data before the data became available in sentence aligned English-Tamil parallel corpus suitable for various NLP tasks. The parallel corpora cover texts from bible, cinema and news domains
Dressing up the woman of sticks: the delightful ambiguities of Czech machine translation
No full textAn interview on machine translation and a new book that introduces the field to the Czech reader
Findings of the 2013 Workshop on Statistical Machine Translation
No full textWe present the results of the WMT13 shared tasks, which included a translation task, a task for run-time estimation of machine translation quality, and an unofficial metrics task. This year, 143 machine translation systems were submitted to the ten translation tasks from 23 institutions. An additional 6 anonymized systems were included, and were then evaluated both automatically and manually, in our largest manual evaluation to date. The quality estimation task had four subtasks, with a total of 14 teams, submitting 55 entries
Special domain data mining through DBpedia on the example of Biology
No full textWikipedia is not only a large encyclopedia, but
lately also a source of linguistic data for various applications.
Individual language versions allow to get the parallel data in multiple languages. Inclusion of Wikipedia articles into categories can be used to filter the language data according to a domain.
In our project, we needed a large number of parallel data for training systems of machine translation in the field of biomedicine. One of the sources was Wikipedia. To select the data from the given domain we used the results of
the DBpedia project, which extracts structured information from the Wikipedia articles and makes them available to users in RDF format.
In this paper we describe the process of data extraction and the problems that we had to deal with, because the open source project like Wikipedia, to which anyone can contribute, is not very reliable concerning consistency
Improvements to Syntax-based Machine Translation using Ensemble Dependency Parsers
No full textDependency parsers are almost ubiqui-
tously evaluated on their accuracy scores,
these scores say nothing of the complex-
ity and usefulness of the resulting struc-
tures. The structures may have more com-
plexity due to their coordination structure
or attachment rules. As dependency parses
are basic structures in which other systems
are built upon, it would seem more reason-
able to judge these parsers down the NLP
pipeline.
We show results from 7 individual parsers,
including dependency and constituent
parsers, and 3 ensemble parsing tech-
niques with their overall effect on a Ma-
chine Translation system, Treex, for En-
glish to Czech translation. We show that
parsers’ UAS scores are more correlated
to the NIST evaluation metric than to the
BLEU Metric, however we see increases
in both metrics
The Design of Eman, an Experiment Manager
Get PDFWe present eman, a tool for managing large numbers of computational experiments. Over
the years of our research in machine translation (MT), we have collected a couple of ideas for
efficient experimenting. We believe these ideas are generally applicable in (computational)
research of any field. We incorporated them into eman in order to make them available in a
command-line Unix environment.
The aim of this article is to highlight the core of the many ideas. We hope the text can serve
as a collection of experiment management tips and tricks for anyone, regardless their field of
study or computer platform they use. The specific examples we provide in eman’s current syntax
are less important but they allow us to use concrete terms. The article thus also fills the gap in eman documentation by providing some high-level overview