Brazilator creating a World Cup Twitter buzz
The CNGL Centre for Global Intelligent Content at DCU and Microsoft Research have collaborated to develop a live tweet translation streaming service for the final stages of the 2014 FIFA World Cup.
Brazilator provides a live translation stream of tweets relating to the 2014 FIFA World Cup, enabling football fans to follow what supporters in 24 of the 32 original competing countries are saying. The system aims to identify the most effective machine translation options for social media content.
12 Languages, 26 Language Pairs
Brazilator instantly translates and streams tweets from 12 languages - Irish, German, French, Spanish, Italian, Portuguese, Croatian, Greek, Japanese, Korean, Chinese, and Farsi - into English. Tweets in English can be translated into each of the other 12 languages.
Fans can visit www.cngl.ie/brazilator, view tweets using popular hashtags such as #WC2014, and follow World Cup postings in their chosen language.
The service presents a graphical analysis of tweets about each match. It also gathers information about user behaviour and how it varies across languages and cultures, thus providing greater insights into social media usage across the world.
Translating tweets presents a significant technical challenge, says Dr Lamia Tounsi, Research Integration Officer with CNGL and Co-Leader of the Brazilator project team.
"Tweets typically contain noisy, diverse and unstructured language, such as incomplete sentences, misspellings, abbreviations, web links, emoticons and hashtags - these are just some of the issues that have to be addressed. The Brazilator World Cup service evaluates machine translation systems and helps to identify the most effective translation options for this type of web content", explains Dr Tounsi.
Working with Microsoft Research, a 20-strong research team at CNGL at Dublin City University (DCU) led by Prof Andy Way is drawing on its expertise to crawl data, build and evaluate machine translation engines, adapt existing engines to the football domain, analyse sentiment, create new Web 2.0 resources, and other relevant tasks.
DCU houses one of the world's leading machine translation groups and has won international recognition for its ability to translate the kind of unstructured language found in social media. CNGL is one of just eleven Microsoft Translator Partners worldwide.
Funded by Science Foundation Ireland and industry partners, CNGL is co-led by DCU and Trinity College Dublin. The centre's 130 researchers are developing advanced technologies to adapt digital content and services to the needs of global users.