论文信息 - Language Segmentation of Twitter Tweets using Weakly Supervised Language Model Induction - 字舞流文

Language Segmentation of Twitter Tweets using Weakly Supervised Language Model Induction

This paper presents early results of a weakly supervised language model induction approach for language segmentation of multilingual texts with a special focus on short texts.

[1] Timothy Baldwin,et al. Automatic Detection and Language Identification of Multilingual Documents , 2014, TACL.

[2] Kenneth R. Beesley,et al. Language Identifier: A Computer Program for Automatic Natural-Language Identification of On-line Tex , 1988 .

[3] Hiroshi Yamaguchi,et al. Text Segmentation by Language Using Minimum Description Length , 2012, ACL.

[4] Jordi Porta,et al. Twitter Language Identification using Rational Kernels and its potential application to Sociolinguistics , 2014, TweetLID@SEPLN.

[5] Riyaz Ahmad Bhat,et al. Language Identification in Code-Switching Scenario , 2014, CodeSwitch@EMNLP.

[6] Hinrich Schütze,et al. Introduction to information retrieval , 2008 .

[7] Arkaitz Zubiaga,et al. Overview of TweetLID: Tweet Language Identification at SEPLN 2014 , 2014, TweetLID@SEPLN.

[8] Julia Hirschberg,et al. Overview for the First Shared Task on Language Identification in Code-Switched Data , 2014, CodeSwitch@EMNLP.

[9] Ted E. Dunning,et al. Statistical Identification of Language , 1994 .

[10] Frank Keller,et al. Using Foreign Inclusion Detection to Improve Parsing Performance , 2007, EMNLP.

[11] Daniel Horowitz,et al. TweetSafa: Tweet Language Identification , 2014, TweetLID@SEPLN.

[12] Ben King,et al. Labeling the Languages of Words in Mixed-Language Documents using Weakly Supervised Methods , 2013, NAACL.