Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages
This work addresses parsing challenges in agglutinative languages, offering a domain-specific solution that is incremental in nature.
The paper tackled dependency parsing for morphologically rich languages by using a convolutional neural network to compose word representations from characters, achieving an average improvement of 3% over the previous best greedy parser on the SPMRL datasets.
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.