Enriching Historic Photography with Structured Data using Image Region Segmentation

no code implementations • LREC 2020 • Taylor Arnold, Lauren Tilton

Manual verification of the extracted annotations yields an accuracy rate of 97. 5{\%}, compared to 70. 7{\%} for relations extracted from object detection and 31. 5{\%} for automatically generated captions.

object-detection Object Detection

Cross-Discourse and Multilingual Exploration of Textual Corpora with the DualNeighbors Algorithm

no code implementations • COLING 2018 • Taylor Arnold, Lauren Tilton

Word choice is dependent on the cultural context of writers and their subjects.

Predicting CEFRL levels in learner English on the basis of metrics and full texts

no code implementations • 28 Jun 2018 • Taylor Arnold, Nicolas Ballier, Thomas Gaillat, Paula Lissòn

The purpose is to build a model for the prediction of learner levels as a function of language complexity features.

A Tidy Data Model for Natural Language Processing using cleanNLP

1 code implementation • 27 Mar 2017 • Taylor Arnold

The package cleanNLP provides a set of fast tools for converting a textual corpus into a set of normalized tables.

coreference-resolution Dependency Parsing +6

Efficient Implementations of the Generalized Lasso Dual Path Algorithm

no code implementations • 13 May 2014 • Taylor Arnold, Ryan Tibshirani

We consider efficient implementations of the generalized lasso dual path algorithm of Tibshirani and Taylor (2011).