Machine learning approaches to coreference resolution are typically supervised, and require expensive labeled data. Some unsupervised approaches have been proposed (e.g., Haghighi...
Chinese is a language that does not have morphological tense markers that provide explicit grammaticalization of the temporal location of situations (events or states). However, i...
Word sketches are part of the Sketch Engine corpus query system. They represent automatic, corpus-derived summaries of the words' grammatical and collocational behaviour. Bes...
Kremena Ivanova, Ulrich Heid, Sabine Schulte im Wa...
Morfette is a modular, data-driven, probabilistic system which learns to perform joint morphological tagging and lemmatization from morphologically annotated corpora. The system i...
Grzegorz Chrupala, Georgiana Dinu, Josef van Genab...
Deep processing of natural language requires large scale lexical resources that have sufficient coverage at a sufficient level of detail and accuracy (i.e. both recall and precisi...