Search Results for author: Steven Neale

Found 10 papers, 0 papers with code

Leveraging Pre-Trained Embeddings for Welsh Taggers

no code implementations WS 2019 Ignatius Ezeani, Scott Piao, Steven Neale, Paul Rayson, Dawn Knight

While the application of word embedding models to downstream Natural Language Processing (NLP) tasks has been shown to be successful, the benefits for low-resource languages is somewhat limited due to lack of adequate data for training the models.

Proceedings of the LexSem+Logics Workshop 2016

no code implementations14 Aug 2016 Steven Neale, Valeria de Paiva, Arantxa Otegi, Alexandre Rademaker

Lexical semantics continues to play an important role in driving research directions in NLP, with the recognition and understanding of context becoming increasingly important in delivering successful outcomes in NLP tasks.

Entity Disambiguation Open Information Extraction +3

QTLeap WSD/NED Corpora: Semantic Annotation of Parallel Corpora in Six Languages

no code implementations LREC 2016 Arantxa Otegi, Nora Aranberri, Antonio Branco, Jan Haji{\v{c}}, Martin Popel, Kiril Simov, Eneko Agirre, Petya Osenova, Rita Pereira, Jo{\~a}o Silva, Steven Neale

This work presents parallel corpora automatically annotated with several NLP tools, including lemma and part-of-speech tagging, named-entity recognition and classification, named-entity disambiguation, word-sense disambiguation, and coreference.

Cross-Lingual Transfer Entity Disambiguation +9

Word Sense-Aware Machine Translation: Including Senses as Contextual Features for Improved Translation Models

no code implementations LREC 2016 Steven Neale, Lu{\'\i}s Gomes, Eneko Agirre, Oier Lopez de Lacalle, Ant{\'o}nio Branco

Although it is commonly assumed that word sense disambiguation (WSD) should help to improve lexical choice and improve the quality of machine translation systems, how to successfully integrate word senses into such systems remains an unanswered question.

Machine Translation Translation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.