Computational Linguistics and & Text Mining Lab's repositories
vua-resources
Lexical resources that are used for semantic parsing by the CLTL modules
Image-Specificity
Reimplementation of Jas & Parikh's (2015) image specificity metric, using word embeddings.
CrowdResultsParser
Parse results from crowd experiments performed in Figure 8 (former Crowdflower) and generate some useful statistics
CEO-Ontology
This repository contains the CEO ontology, the evaluation corpus and the CEO vocabulary.
WordNetSimilarity
Programs and scripts that test performance of WordNet similarity measurements using different settings
WordNet_Ambiguity
This repository provides a way to compute the WordNet ambiguity of a sequence of text.
ELBaselines
This repo is aimed to create baseline results for Entity Linking, by running a text against the state-of-the-art systems for entity linking, using their most standard configuration.
HELAnalysis
Analysis of the Human-like Entity Linking system
NewsAcquisition
Analysis and acquisition of news data from the Signal Media corpus and other news collections
cltl_kyoto_scripts
Miscellaneous scripts on kyoto.let.vu.nl
nwr-semeval2018-5
NewsReader participation to task 5 of SemEval2018
SemEval2018-5_Postprocessing
Postprocessing steps for the SemEval-2018 task 5: Counting events and participants in the long tail
StoryTeller
Toolkit to query the NewsReader KnowledgeStore with SPARQL and create a JSON story
FrameNet-annotation-tool
Python-based command-line tool for FrameNet annotation
GroundedTranslation
Multilingual image description
coreference-evaluation
Evaluation package for event coreference using the reference-scorer
DutchDescriptions
Dutch descriptions for the Flickr30K validation and test data, plus a cross-lingual comparison tool.