Efficient Second-Order TreeCRF for Neural Dependency Parsing

ACL 2020  ·  Yu Zhang, Zhenghua Li, Min Zhang ·

In the deep learning (DL) era, parsing models are extremely simplified with little hurt on performance, thanks to the remarkable capability of multi-layer BiLSTMs in context representation. As the most popular graph-based dependency parser due to its high efficiency and performance, the biaffine parser directly scores single dependencies under the arc-factorization assumption, and adopts a very simple local token-wise cross-entropy training loss. This paper for the first time presents a second-order TreeCRF extension to the biaffine parser. For a long time, the complexity and inefficiency of the inside-outside algorithm hinder the popularity of TreeCRF. To address this issue, we propose an effective way to batchify the inside and Viterbi algorithms for direct large matrix operation on GPUs, and to avoid the complex outside algorithm via efficient back-propagation. Experiments and analysis on 27 datasets from 13 languages clearly show that techniques developed before the DL era, such as structural learning (global TreeCRF loss) and high-order modeling are still useful, and can further boost parsing performance over the state-of-the-art biaffine parser, especially for partially annotated training data. We release our code at https://github.com/yzhangcs/crfpar.

PDF Abstract ACL 2020 PDF ACL 2020 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Dependency Parsing CoNLL-2009 CRFPar LAS 86.52 # 1
UAS 89.63 # 1
Dependency Parsing NLPCC-2019 CRFPar LAS 72.33 # 1
UAS 78.02 # 1
Dependency Parsing Penn Treebank CRFPar UAS 96.14 # 10
LAS 94.49 # 10


No methods listed for this paper. Add relevant methods here