Localization

Review
TermSuite: Open source
TermSuite is an open source and
platform-independent TET written
in Java and distributed under the
Apache License 2.0. It was developed
within the scope of the TTC (Terminology
Extraction, Translation Tools
and Comparable Corpora) project,
whose purpose was to design a tool
capable of extracting bilingual terminology
from comparable corpora
in six languages: English, French,
German, Spanish, Chinese and Russian.
TTC TermSuite's architecture
is composed of three modules: the
Spotter, the Indexer and the Aligner.
The Spotter module is responsible
for preprocessing the input monolingual
corpus, meaning it performs
tokenization, part-of-speech tagging,
stemming and lemmatization. Then,
the Indexer module uses both a statistic
and a linguistic-based approach
to extract monolingual terminology
from a monolingual corpus processed
by the Spotter. Finally, the
Aligner computes the translation of a
source terminology into a target language.
The source and target terms
required are those already computed
by the Indexer module, which means
that the previous two steps should be
repeated for the target language. The
user can choose from several alignment
options, such as the selection of
the maximum number of translation
candidates for a given source term,
the use of similarity measures to
compare the contexts of the term in
the source and the target languages,
amongst other advanced settings.
Once all the parameters are set, it
is possible to view and explore all
the translation candidates ranked
according to their similarity score
within the tool or use the output
XML file for other purposes.
SDL MultiTerm
SimpleExtractor
Web-based terminology
extraction tools
Although standalone TETs still
are predominant in today’s market,
TermSuite
Sketch Engine
Bilingual extraction X X X
Source and target context
comparison
X
Translated
Terminus
Kea
Rainbow
Terms validation X X X X X X X
Bilingual dictionaries
compilation X X
Context extraction X X X X X X X X
JATE
Support various file
formats X X X X X X X X
Rank terms by frequency X X X X X X
Support for many
languages X X X X X X X
Specify the minimal
number of occurrences X X X X X X X
Show linguistic
information X X X
Specify the maximum
number of translations
Stopword list option X X X X X X
Choose the minimum
and maximum number of
words per term
X
X X X X X
Term statistics X X X X X X X X X
Figure 1: Comparison of extraction tools.
future web-based technologies will
certainly evolve by migrating all
standalone features to a web-based
environment, which will allow these
tools to take over market leadership
16 April/May 2016