P
Paul Cook
Researcher at University of New Brunswick
Publications - 74
Citations - 3276
Paul Cook is an academic researcher from University of New Brunswick. The author has contributed to research in topics: Word (computer architecture) & SemEval. The author has an hindex of 26, co-authored 74 publications receiving 2938 citations. Previous affiliations of Paul Cook include University of Toronto & University of Melbourne.
Papers
More filters
Proceedings ArticleDOI
Low Resource Dependency Parsing: Cross-lingual Parameter Sharing in a Neural Network Parser
TL;DR: This work proposes a learning method that needs less data, based on the observation that there are underlying shared structures across languages, and exploits cues from a different source language in order to guide the learning process.
Journal ArticleDOI
Text-based twitter user geolocation prediction
Bo Han,Paul Cook,Timothy Baldwin +2 more
TL;DR: This paper presents an integrated geolocation prediction framework, and evaluates the impact of nongeotagged tweets, language, and user-declared metadata on geolocated prediction, and discusses how users differ in terms of their geolocatability.
Proceedings Article
How Noisy Social Media Text, How Diffrnt Social Media Sources?
TL;DR: This work investigates just how linguistically noisy or otherwise text in social media text is over a range of social media sources, in the form of YouTube comments, Twitter posts, web user forum posts, blog posts and Wikipedia, which is compared to a reference corpus of edited English text.
Proceedings Article
Automatically Constructing a Normalisation Dictionary for Microblogs
Bo Han,Paul Cook,Timothy Baldwin +2 more
TL;DR: This paper proposes a method for constructing a dictionary of lexical variants of known words that facilitates lexical normalisation via simple string substitution and shows that a dictionary-based approach achieves state-of-the-art performance for both F-score and word error rate on a standard dataset.
Journal ArticleDOI
Unsupervised type and token identification of idiomatic expressions
TL;DR: This article develops statistical measures that each model a specific property of idiomatic expressions by looking at their actual usage patterns in text, and uses some of the measures in a token identification task where they distinguish idiomatic and literal usages of potentially idiomatic expression in context.