Search Results for author: Lance De Vine

Found 5 papers, 1 papers with code

Unsupervised Mining of Analogical Frames by Constraint Satisfaction

1 code implementation ALTA 2018 Lance De Vine, Shlomo Geva, Peter Bruza

It has been demonstrated that vector-based representations of words trained on large text corpora encode linguistic regularities that may be exploited via the use of vector space arithmetic.

Language Acquisition Machine Translation +1

The Benefits of Word Embeddings Features for Active Learning in Clinical Information Extraction

no code implementations ALTA 2016 Mahnoosh Kholghi, Lance De Vine, Laurianne Sitbon, Guido Zuccon, Anthony Nguyen

This study investigates the use of unsupervised word embeddings and sequence features for sample representation in an active learning framework built to extract clinical concepts from clinical free text.

Active Learning Informativeness +1

Parallel Streaming Signature EM-tree: A Clustering Algorithm for Web Scale Applications

no code implementations21 May 2015 Christopher M. de Vries, Lance De Vine, Shlomo Geva, Richi Nayak

We introduce a scalable algorithm that clusters hundreds of millions of web pages into hundreds of thousands of clusters.

Clustering

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