Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages

Abstract

We present a transition-based dependency parser that uses a convolutional neural network to compose word representations from characters. The character composition model shows great improvement over the word-lookup model, especially for parsing agglutinative languages. These improvements are even better than using pre-trained word embeddings from extra data. On the SPMRL data sets, our system outperforms the previous best greedy parser (Ballesteros et al., 2015) by a margin of 3% on average.

Accepted in ACL 2017 (Short)

References in corpus (2)

• Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs
• Structured Training for Neural Network Transition-Based Parsing

Cited by in corpus (4)

• Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech
• A General-Purpose Tagger with Convolutional Neural Networks
• Exploiting Synchronized Lyrics And Vocal Features For Music Emotion Detection
• Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrieval