Computational Linguistics and & Text Mining Lab

MFS_classifier

This repo contains the scripts to attempt to remove the mfs bias from a WSD system.

LongTailIdentity

Generating profiles of long tail identities from text

WordNetMapper

This repo provides the possibility to map between lexical keys | offsets | ilidefs from one wordnet version to the other ["16","17","171","20","21","30"]. It makes use of the index.sense files from WordNet (http://wordnet.princeton.edu/) and the automatically generated mappings between WordNet offsets (http://nlp.lsi.upc.edu/tools/download-map.php)

morphosyntactic_parser_nl

Morphosyntactic parser for Dutch based on the Alpino parser

EL-long-tail-phenomena

Systematic study of long tail phenomena in the task of entity linking

svm_wsd

Word Sense Disambiguation system developed on the DutchSemCor project using Support Vector Machines. The input is plain text, and the output XML

hpsp

Experiments with hyperspace models for selectional preference

BabelfyReimplementation

Reimplementation of Babelfy (http://babelfy.org)

relink

RElinking with CONtext - Entity linking module

positive-interpretations

Code (Python 3.6) for automatically scoring and classifying positive interpretations generated from negations in OntoNotes

GRaSP

opinion_miner_deluxe

Opinion miner based of Machine Learning that can be trained on a corpus of KAF/NAF files

vua_factuality

factuality_experimental_environment

multilingual_factuality

EmotionTagger

Uses an emotion tagger to tag text with emotions

EventStoryLine

Materials for the StoryLine extraction task - annotated data, baselines and evaluation scripts, evaluation data.

OpeNER_corpus

OpeNER corpus : news articles and hotel reviews annotated with opinion expressions, holders, targets and their relations

TimeMLEventTrigger

LongTailQATask

LOTUS

Code of LOTUS, the largest LOD text index, allowing free text access to the LOD Laundromat data collection

SemanticOverfitting

LSTM-WSD

MoreIsNotAlwaysBetter

HumanLikeEL

Human-Like Entity Linking using Contextual knowledge

Profiling

Extraction and categorization of world knowledge about people from WIkidata for the sake of creating profiles

cltl-magicplace

Annotate NAF-documents with the Newsreader pipeline on Lisa computer (SurfSara)

nwr-triple-api

Queries the KnowledgeStore populated with NewsReader output and represents the result as SEM-RDF or SEM-JSON

OldBailey

Processing the OldBailey data to create LOD

Spoken-versus-Written

Code and data for our VarDial 2018 paper on spoken versus written image descriptions