@inproceedings{ea058571bbcf4f429c4c5ea773e09025,
title = "Learning polylingual topic models from code-switched social media documents",
abstract = "Code-switched documents are common in social media, providing evidence for polylingual topic models to infer aligned topics across languages. We present Code-Switched LDA (csLDA), which infers language specific topic distributions based on code-switched documents to facilitate multi-lingual corpus analysis. We experiment on two code-switching corpora (English-Spanish Twitter data and English-Chinese Weibo data) and show that csLDA improves perplexity over LDA, and learns semantically coherent aligned topics as judged by human annotators.",
author = "Nanyun Peng and Yiming Wang and Mark Dredze",
year = "2014",
doi = "10.3115/v1/p14-2110",
language = "English (US)",
isbn = "9781937284732",
series = "52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "674--679",
booktitle = "Long Papers",
address = "United States",
note = "52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 ; Conference date: 22-06-2014 Through 27-06-2014",
}