Search Machine Learning Repository:
Learning Character-level Representations for Part-of-Speech Tagging
Authors: Cicero D. Santos and Bianca Zadrozny
Conference: Proceedings of the 31st International Conference on Machine Learning (ICML-14)
Abstract: Distributed word representations have recently been proven to be an invaluable resource for NLP. These representations are normally learned using neural networks and capture syntactic and semantic information about words. Information about word morphology and shape is normally ignored when learning word representations. However, for tasks like part-of-speech tagging, intra-word information is extremely useful, specially when dealing with morphologically rich languages. In this paper, we propose a deep neural network that learns character-level representation of words and associate them with usual word representations to perform POS tagging. Using the proposed approach, while avoiding the use of any handcrafted feature, we produce state-of-the-art POS taggers for two languages: English, with 97.32% accuracy on the Penn Treebank WSJ corpus; and Portuguese, with 97.47% accuracy on the Mac-Morpho corpus, where the latter represents an error reduction of 12.2% on the best previous known result.
authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).