Conta-me Histórias [http://contamehistorias.pt] is a temporal summarization framework of news articles that allows users to explore and revisit events in the past. To select relevant stories of different time-periods, we rely on YAKE! [http://yake.inesctec.pt] a keyword extraction algorithm devel...
LX Semantic Similarity is an online service for measuring the semantic similarity between words in Portuguese. This service uses the LX-DSemVectors, a distributional semantics model (a.k.a. word embeddings) of the Portuguese language. The model represents each word in its vocabulary by a vecto...
LX-Quantitative is an online service for the quantitative analysis of texts along a range of linguistic metrics. This service is based on automatic text processing tools. Hence, the results it returns may not be always totally correct. Its high accuracy rate tough allows it to provide a useful...
LX-Translator is a freely available on-line service for translation between Portuguese and Chinese. This service was developed and is maintained at the University of Lisbon by the NLX-Natural Language and Speech Group of the Department of Informatics. Intrinsic evaluation of the model for the ...
SenseClusters is a package of (mostly) Perl programs that allows a user to cluster similar contexts together using unsupervised knowledge-lean methods.
FEUP CoRef is a freely available online service for coreference resolution in Portuguese and Spanish. This service was developed and is maintained at the Faculdade de Engenharia da Universidade do Porto Department of Informatics.
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.
VISTA@UE-SA is a freely available on-line service for the sentiment analysis of short sentences (tweets) in Portuguese. This service was developed and is maintained at the University of Evora by the VISTA - Video, Image, Speech, and Text Analysis Group of the Department of Informatics.
This is a UIMA wrapper for the OpenNLP Tokenizer tool. It splits English sentences into individual tokens. The tool forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record) for building and evaluating text mining workflows. The U-Comp...
Technical Description: http://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf http://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf http://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf