Character-based feature extraction with LSTM networks for POS-tagging task
- 1 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
In this paper we describe a work in progress on designing the continuous vector space word representations able to map unseen data adequately. We propose a LSTM-based feature extraction layer that reads in a sequence of characters corresponding to a word and outputs a single fixed-length real-valued vector. We then test our model on a POS tagging task on four typologically different languages. The results of the experiments suggest that the model can offer a solution to the out-of-vocabulary words problem, as in a comparable setting its OOV accuracy improves over that of a state of the art tagger.Keywords
This publication has 13 references indexed in Scilit:
- Deep learningNature, 2015
- Data-Driven Morphological Analysis and Disambiguation for Kazakh2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- On certain aspects of Kazakh part-of-speech tagging2014
- Rule Based Morphological Analyzer of Kazakh Language2014
- Glove: Global Vectors for Word Representation2014
- Convolutional Neural Networks for Sentence Classification2014
- Long Short-Term MemoryNeural Computation, 1997
- Producing high-dimensional semantic spaces from lexical co-occurrenceBehavior Research Methods, Instruments, & Computers, 1996
- Finding structure in timeCognitive Science, 1990