This resource contains model weights for five Transformer-based models: RoBERTa, GPT-2, T5, BART and COMET(BART). These models were implemented using HuggingFace, and fine-tuned on the following four commonsense reasoning tasks: Argument Reasoning Comprehension Task (ARCT), AI2 Reasoning Challen...
Treebanks and semantic lexicons for Basque, Bulgarian, Dutch, German and Portuguese. Created within European project QTLeap.
In order to construct the inventory, we firstly compiled a species name dictionary by combining all of the names available in Catalogue of Life (CoL), Encyclopedia of Life (EoL) and Global Biodiversity Information Facility (GBIF). The terms contained in this dictionary were then located within ...
This set of materials resulted from a study on the processing of explicit pronouns in European Portuguese. A spreadsheet containing data from 75 participants (young adults), namely, per-word reading times and accuracy data on comprehension questions, is provided. Complementary materials (Read Fir...
This tool performs tokenization of text and assigns all possible morphological analyses to each token. These analyses include the base form of the token, part-of-speech, information about number and gender. The morphological analyser is a module of Apertium machine translation system. The provide...
MaltParser is a system for data-driven dependency parsing, which can be used to induce a parsing model from treebank data and to parse new data using an induced model. MaltParser is developed by Johan Hall, Jens Nilsson and Joakim Nivre at Växjö University and Uppsala University, Sweden (see Nivr...
Tokenisation is one of the functionalities of the GENIA tagger, which additionally outputs the base forms, part-of-speech tags, chunk tags, and named entity tags. The tagger is specifically tuned for biomedical text such as MEDLINE abstracts. The tool is a UIMA component, which forms part of th...
This dataset has been created within the framework of the European Language Resource Coordination (ELRC) Connecting Europe Facility - Automated Translation (CEF.AT) action. For further information on the project: http://lr-coordination.eu. English-Slovak corpus of annual reports on immigration a...
This dataset has been created within the framework of the European Language Resource Coordination (ELRC) Connecting Europe Facility - Automated Translation (CEF.AT) action. For further information on the project: http://lr-coordination.eu. Dataset of various English-Slovak legal texts within age...
In the period since 2004, many novel sophisticated approaches for generic multi-document summarization have been developed. Intuitive simple approaches have also been shown to perform unexpectedly well for the task. Yet it is practically impossible to compare the existing approaches directly, bec...