Stack-Pointer Networks for Dependency Parsing

By Xuezhe Ma, Zecong Hu, Jingzhou Liu, Nanyun Peng, Graham Neubig, Eduard H. Hovy. 2018

172 citations recorded by the source corpus.

We introduce a novel architecture for dependency parsing: stack-pointer networks (StackPtr). Combining pointer networks (Vinyals et al., 2015) with an internal stack, the proposed model first reads and encodes the whole sentence, then builds the dependency tree top-down (from root-to-leaf) in a depth-first fashion. The stack tracks the status of the depth-first search and the pointer networks select one child for the word at the top of the stack at each step. The StackPtr parser benefits from the information of whole sentence and all previously derived subtree structures, and removes the left-to-right restriction in classical transition-based parsers. Yet the number of steps for building any (non-projective) parse tree is linear in the length of the sentence just as other transition-based parsers, yielding an efficient decoding algorithm with O(n^2) time complexity. We evaluate our model on 29 treebanks spanning 20 languages and different dependency annotation schemas, and achieve state-of-the-art performances on 21 of them

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Semi-Supervised Sequence Modeling with Cross-View Training (2018, neutral): “…2017) 96.37 ± 0.05 91.93 ± 0.19 ELMo † (Peters et al., 2018) 92.22 ± 0.10 NPM (Ma and Hovy, 2017) 94.9 93.0 Deep Biafﬁne (Dozat and Manning, 2017) 95.74 94.08 Stack Pointer (Ma et al., 2018) 95.87 94.19 Stanford (Luong and Manning, 2015) 23.3 Google (Luong et al., 2017) 26 5: Results on the test…”
Towards Explainable NLP: A Generative Explanation Framework for Text Classification (2018, background): “Deep learning methods have produced state-of-the-art results in many natural language processing (NLP) tasks (Vaswani et al., 2017; Yin et al., 2018; Peters et al., 2018; Wang et al., 2018; Han-cock et al., 2018; Ma et al., 2018).”
Head-Driven Phrase Structure Grammar Parsing on Penn Treebank (2019, methodology): “These models attain state-of-the-art results for dependency parsing (Chen and Man-ning, 2014; Dozat and Manning, 2017; Ma et al., 2018) and constituent parsing (Dyer et al., 2016; Cross and Huang, 2016; Kitaev and Klein, 2018a).”
Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT (2019, methodology): “All BERT models show significant improvement over the baselines for both languages, and outperform the previous state-of-the-art approaches using cross-view training (Clark et al. 2018) and stack-pointer networks (Ma et al. 2018) by 0.29% and 3% in LAS for English and Chinese, respectively.”
Deep Contextualized Self-training for Low Resource Dependency Parsing (2019, methodology): “Finally, we compare to the cross-view training algorithm (CVT) (Clark et al., 2018), that was developed for semi-supervised learning with DNNs. 7 Hyper-parameters We employ the BiAFFINE parser implementation of Ma et al. (2018).”
SG-Net: Syntax-Guided Machine Reading Comprehension (2019, background): “Recently, dependency syntactic parsing have been further developed with neural network and attained new state-of-the-art results (Zhang, Zhao, and Qin 2016; Li et al. 2018; Ma et al. 2018; Li, Zhao, and Parnow 2020).”
FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow (2019, result): “This technique is similar to the “masked language model” in previous studies (Melamud et al., 2016; Devlin et al., 2018; Ma et al., 2018).”
Joint Parsing and Generation for Abstractive Summarization (2019, background): “There have been a variety of studies examining neural dependency parsers us-ing transition-and graph-based algorithms (Dyer et al. 2015; Kiperwasser and Goldberg 2016; Dozat and Manning 2017; Ma et al. 2018).”