Part-of-Speech Tagging

Our part-of-speech tagger uses the generalized model from dynamic model selection and utilizes ambiguity classes trained on a large corpus. It processes over 82K tokens per second on an Intel Xeon 2.30GHz machine and shows the state-of-the-art accuracy (97.64% on the WSJ corpus).

• Dynamic Feature Induction: The Last Gist to the State-of-the-Art, Jinho D. Choi, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (NAACL'16), San Diego, CA, 2016.
• Intrinsic and Extrinsic Evaluations of Word Embeddings, Michael Zhai, Johnny Tan, Jinho D. Choi, Proceedings of the AAAI 2015 Student Program, Phoenix, AZ, 2015.
• Fast and Robust Part-of-Speech Tagging Using Dynamic Model Selection, Jinho D. Choi, Martha Palmer, Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL'12), 363-367, Jeju, Korea, 2012.

English Tags