CIRCL: Yohamy Polanco

MAR 02, 2021 | 6:30 PM TO 8:30 PM

Details

WHERE:

Online Event

WHEN:

March 02, 2021: 6:30 PM-8:30 PM

ADMISSION:

Free

SPONSOR:

Linguistics Program

Description

Yohamy Polanco will present:

A Computational study in the detection of English-Spanish code-switches

Abstract: 
Code-switching is the linguistic phenomenon where a multilingual person alternates between two or more languages in a conversation, whether that be spoken or written. This thesis studies the automatic detection of code-switching occurring specifically between English and Spanish in two corpora. Twitter and other social media sites have provided an abundance of linguistic data that is avail-able to researchers to perform countless experiments. Collecting the data is fairly easy if a study is on monolingual text, but if a study requires code-switched data, this becomes a complication as APIs only accept one language as a parameter. This thesis focuses on identifying code-switching in both Twitter data and the Miami-Bangor corpus. This is done by conducting three different experiments. Our first experiment is a logistic regression model where we attempt to distinguish code-switched data from monolingual data. The second experiment is using a novel Word2Vecaverage nearest neighbor (WANN) classifier based on word embeddings to detect code-switching. The third experiment uses Doc2Vec, where the model uses the mean vector of each document to learn and distinguish between code-switched and monolingual data. Each of these experiments are performed twice, once with tweets and once with the Miami Bangor corpus. The results show that the WANN model performs best on Twitter data. The Doc2Vec model performs best on the Miami Bangor corpus. However, both approaches did well and the performances are comparable.

Zoom links will be sent individually