Paper: A Joint Language Model With Fine-grain Syntactic Tags

ACL ID D09-1116
Title A Joint Language Model With Fine-grain Syntactic Tags
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2009
  • Denis Filimonov (University of Maryland, College Park MD)
  • Mary P. Harper (University of Maryland, College Park MD; Johns Hopkins University, Baltimore MD)

We present a scalable joint language model designed to utilize fine-grain syn- tactic tags. We discuss challenges such a design faces and describe our solutions that scale well to large tagsets and cor- pora. We advocate the use of relatively simple tags that do not require deep lin- guistic knowledge of the language but pro- vide more structural information than POS tags and can be derived from automati- cally generated parse trees – a combina- tion of properties that allows easy adop- tion of this model for new languages. We propose two fine-grain tagsets and evalu- ate our model using these tags, as well as POS tags and SuperARV tags in a speech recognition task and discuss future direc- tions.