Joint POS Tagging and Transition-based Constituent Parsing in Chinese with Non-local Features

By Zhiguo Wang, Nianwen Xue. 2014

42 citations recorded by the source corpus.

We propose three improvements to address the drawbacks of state-of-the-art transition-based constituent parsers. First, to resolve the error propagation problem of the traditional pipeline approach, we incorporate POS tagging into the syntactic parsing process. Second, to alleviate the negative influence of size differences among competing action sequences, we align parser states during beam-search decoding. Third, to enhance the power of parsing models, we enlarge the feature set with non-local features and semisupervised word cluster features. Experimental results show that these modifications improve parsing performance significantly. Evaluated on the Chinese TreeBank (CTB), our final performance reaches 86.3% (F1) when trained on CTB 5.1, and 87.1% when trained on CTB 6.0, and these results outperform all state-of-the-art parsers.

Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing

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 Molecular Biology

In Natural Language Processing

Citations in the corpus

Recurrent Neural Network Grammars (2016, background): “.1. Model type F 1 Zhu et al. (2013) D 82.6 Wang et al. (2015) D 83.2 Huang and Harper (2009) D 84.2 Charniak (2000) G 80.8 Bikel (2004) G 80.6 Petrov and Klein (2007) G 83.3 Zhu et al. (2013) S 85.6 Wang and Xue (2014) S 86.3 Wang et al. (2015) S 86.6 Discriminative, q(y jx) D 80.7 Generative, p^(y”
Stack-propagation: Improved Representation Learning for Syntax (2016, background): “As an alternative, a wide range of prior work has investigated jointly modeling both POS and parse trees (Li et al., 2011; Hatori et al., 2011; Bohnet and Nivre, 2012; Qian and Liu, 2012; Wang and Xue, 2014; Li et al., 2014; Zhang et al., 2015; Alberti et al., 2015).”
In-Order Transition-based Constituent Parsing (2017, unknown): “The in-order parser achieves the best results under hte fully-Model 86.9 Top-down parser 86.9 Bottom-up parser 87.5 In-order parser 88.0 semi-supervision Zhu et al. (2013) 85.6 Wang and Xue (2014) 86.3 Wang et al. (2015) 86.6 Table 6: Final results on test set of CTB. supervised setting.”
Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT (2019, background): “ALL OOV Zhang et al. (2015) 94.47∗ n/a Zhang et al. (2014) 94.62∗ n/a Kurita, Kawahara, and Kurohashi (2017) 94.84∗ n/a Hatori et al. (2011) 94.64 n/a Wang and Xue (2014) 96.0 n/a Baseline 95.65 (±0.26) 83.57 (±0.55) Baseline \ BERT 96.38 (±0.15) 88.13 (±0.72) Baseline + BERT 97.25 (±0.18) 90.53…”
Feature Optimization for Constituent Parsing via Neural Networks (2015, methodology): “Although our system only utilizes some basic primitive units (in Table 1(a)), it still outperforms Wang and Xue (2014)’s shift-reduce parsing system which uses more complex structural features and semi-supervised word cluster features.”