<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T05:49:57Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/25126" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/25126</identifier><datestamp>2026-09-24T01:54:09Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Chen, Jun</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Cui, Yexin</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2020-01-02T17:13:12Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2020-01-02T17:13:12Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2020</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/25126</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/9799</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Language identification is the task of automatically detecting the languages(s) written in a text or a document given, and is also the very first step of further natural language processing tasks. This task has been well-studied over decades in the past, however, most of the works have focused on long texts rather than the short that is proved to be more challenging due to the insufficiency of syntactic and semantic information. In this work, we present approaches to this problem based on deep learning techniques, traditional methods and their combination. The proposed ensemble model, composed of a learning based method and a dictionary based method, achieves 89.6% accuracy on our new generated gold test set, surpassing Google Translate API by 3.7% and an industry leading tool Langid.py by 26.1%.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Master of Applied Science (MASc)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Natural Language Processing</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Language identification</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Textual data</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Language Identification on Short Textual Data</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>