English Recipe Flow Graph Corpus

no code implementations • LREC 2020 • Yoko Yamakata, Shinsuke Mori, John Carroll

For r-NE tagging we train a deep neural network NER tool; to compute flow graphs we train a dependency-style parsing procedure which we apply to the entire sequence of r-NEs in a recipe. In evaluations, our systems achieve 71. 1 to 87. 5 F1, demonstrating that our annotation scheme is learnable.

NER

Using Linguistic Data for English and Spanish Verb-Noun Combination Identification

no code implementations • COLING 2016 • Uxoa I{\~n}urrieta, Arantza D{\'\i}az de Ilarraza, Gorka Labaka, Kepa Sarasola, Itziar Aduriz, John Carroll

We present a linguistic analysis of a set of English and Spanish verb+noun combinations (VNCs), and a method to use this information to improve VNC identification.

Chunking Machine Translation

Learning to Predict Distributions of Words Across Domains

no code implementations • ACL 2014 • Danushka Bollegala, David Weir, John Carroll

Chunking Domain Adaptation +3

Chunking Clinical Text Containing Non-Canonical Language

no code implementations • WS 2014 • Aleks Savkov, ar, John Carroll, Jackie Cassell

Chunking Constituency Parsing +2

Induction of Root and Pattern Lexicon for Unsupervised Morphological Analysis of Arabic

no code implementations • IJCNLP 2013 • Bilal Khaliq, John Carroll

Morphological Analysis

Unsupervised Induction of Arabic Root and Pattern Lexicons using Machine Learning

no code implementations • RANLP 2013 • Bilal Khaliq, John Carroll

BIG-bench Machine Learning Morphological Analysis