Gervásio PT-* is a foundation, large language model for the Portuguese language. It is a decoder of the GPT family, based on the neural architecture Transformer and developed over the Pythia model, with competitive performance for this language. It has different versions that were trained for ...
ixa-pipe-coref-eu is a Basque coreference resolution tool, which is an adaptation of Stanford Deterministic Coreference Resolution (http://www-nlp.stanford.edu/downloads/dcoref.shtml). This tool reads a text document annotated with lemmas, named entities and constituents formated in Natural La...
Web service created by exporting UIMA-based workflow from the U-Compare text mining system. Functionality: Performs discourse parsing on plain text. Also identifies sentences, tokens, parts of speech, lemmas, clauses and coreference chains Tools in workflow: UAIC-POSTagger, UAIC-NPChunker, UAI...
This inventory contains a set of terms that are relevant to the study of medical history. The inventory is organised as a set of "heading terms", belonging to one of seven different semantic categories, each of which is accompanied by a set of semantically-related terms. There are around 175,0...
The GENIA tagger analyzes English sentences and 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.
Lince is a multi-platform stand-alone application that updates the textual contents of documents in a range of popular formats to the spelling prescribed by the 1990 Portuguese language reform. It works with both previously existing Portuguese language orthographic standards (1943, previously val...
Enju is a syntactic parser for English. The grammar used by the parser is based on Head Driven Phrase Structure Grammar (HPSG). Enju can analyse syntactic/semantic structures of English sentences can output phrase structure and predicate-argument structures.
These are manually annotated corpora for teaching and learning purposes of Brazilian Portuguese, Dutch, Estonian, and Slovene, as a contribution to the Manually Annotated Corpora Family available in CLARIN. Sentences are annotated with “problematic” or “non-problematic” labels, from the point of ...
A wordnet is a lexical database. It groups synonymous words into sets, the synsets, which represent distinct concepts. These synsets form nodes in a network, which are interlinked through edges that correspond to semantic relations between those synsets. For instance, the hypernym relation, also ...
ViPER is a verb lexical database with +7,000 verb senses, along with their structural, distributional, and transformational properties. The verb senses are classified based on the main syntactic properties of their construction. Around 70 formal classes have been devised. For each verb sense, its...