Yake! (Campos et al. 2020) is a novel feature-based system for multi-lingual keyword extraction, which supports texts of different sizes, domain or languages. Unlike most of the systems, Yake! does not rely on dictionaries nor thesauri, neither is trained against any corpora. Instead, we follow a...
Uplug (see Tiedemann, 2003a) is a collection of tools and scripts for processing text-corpora, for automatic alignment and for term extraction from parallel corpora. Several tools have been integrated in Uplug. Pre-processing tools include a sentence splitter, a general tokenizer and wrappers a...
TinySVM is an implementation of Support Vector Machines (SVMs) (Vapnik, 1995; Vapnik, 1998) for the problem of pattern recognition.
The U-Compare Workbench is a graphical user interface that operates on top of the U-Compare platform. The U-Compare platform allows users to build and evaluate NLP workflows. Workflows consist of one or more components, consisting of corpus readers and tools, such as tokenisers, POS taggers, name...
YamCha is a generic, customizable, and open source text chunker oriented toward a lot of NLP tasks, such as POS tagging, Named Entity Recognition, base NP chunking, and Text Chunking. We used it for NP chunking.
Bilingual concordancer is a language independent concordancer tool for bilingual concordancing, translation revision, post-editing, etc. Note that the tool is also able to be used as a monolingual concordancer. Several corpora are also included in this resource.
The purpose of the U-Compare platform is to facilitate easy and rapid development and evaluation of NLP and text mining systems. It includes utilities (including a graphical user interface, the U-Compare workbench, see separate record in META-SHARE) to create workflows from individual, interopera...
Web service created by exporting UIMA-based workflow from the U-Compare text mining system. Functionality: Identifies paragraphs in plain text Tools in workflow: MLRS Paragraph Splitter (University of Malta) NOTE: The licence provided covers the web service only. Tools used to create the workf...
ACOPOST is a free and open source collection of four part-of-speech taggers (t3, met, tbt, and et). In corpus linguistics, part-of-speech tagging (POS tagging or POST), also called grammatical tagging or word-category disambiguation, is the process of marking up the words in a text (corpus) as co...
MSTParser is a non-projective dependency parser (see McDonald et al., 2005a, 2006) that searches for maximum spanning trees over directed graphs. Models of dependency structure are based on large-margin discriminative training methods (see McDonald et al., 2005b). Projective parsing is also suppo...