Search Results for author: Victor Soto

Found 7 papers, 1 papers with code

Combining Weakly Supervised ML Techniques for Low-Resource NLU

no code implementations NAACL 2021 Victor Soto, Konstantine Arkoudas

Accordingly, unsupervised learning and SSL (semi-supervised learning) techniques continue to be of vital importance.

Continual Learning Data Augmentation +2

Named Entity Recognition on Code-Switched Data: Overview of the CALCS 2018 Shared Task

no code implementations WS 2018 Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Mona Diab, Julia Hirschberg, Thamar Solorio

In the third shared task of the Computational Approaches to Linguistic Code-Switching (CALCS) workshop, we focus on Named Entity Recognition (NER) on code-switched social-media data.

named-entity-recognition Named Entity Recognition +2

Crowdsourcing Universal Part-Of-Speech Tags for Code-Switching

no code implementations24 Mar 2017 Victor Soto, Julia Hirschberg

We split the annotation task into three subtasks: one in which a subset of tokens are labeled automatically, one in which questions are specifically designed to disambiguate a subset of high frequency words, and a more general cascaded approach for the remaining data in which questions are displayed to the worker following a decision tree structure.

An urn model for majority voting in classification ensembles

1 code implementation NeurIPS 2016 Victor Soto, Alberto Suárez, Gonzalo Martinez-Muñoz

An analysis of this classical urn model based on the hypergeometric distribution makes it possible to estimate the confidence on the outcome of majority voting when only a fraction of the individual predictions is known.

Classification General Classification

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