Neural Transition-based Syntactic Linearization
This work addresses the task of syntactic linearization for natural language processing, presenting an incremental improvement over existing neural methods.
The paper tackles the problem of syntactic linearization, which involves ordering words into a grammatical sentence with its syntactic tree, and reports that their neural transition-based model achieves significantly better results than LSTM language models on this task.
The task of linearization is to find a grammatical order given a set of words. Traditional models use statistical methods. Syntactic linearization systems, which generate a sentence along with its syntactic tree, have shown state-of-the-art performance. Recent work shows that a multi-layer LSTM language model outperforms competitive statistical syntactic linearization systems without using syntax. In this paper, we study neural syntactic linearization, building a transition-based syntactic linearizer leveraging a feed-forward neural network, observing significantly better results compared to LSTM language models on this task.