---
title: "Fast and Accurate Shift-Reduce Constituent — Zhu 2013"
description: "Transition-based dependency parsers with beam search and global training already match chart-based parsers, but shift-reduce constituent parsers have…"
authors: ["Muhua Zhu", "Yue Zhang", "Wenliang Chen", "Min Zhang", "Jingbo Zhu"]
year: 2013
venue: "Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/P13-1043/"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhu-2013-fast-accurate-shift-reduce-constituent/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhu-2013-fast-accurate-shift-reduce-constituent/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2013](https://md.research.elamur.ai/free/en/papers/2013/) / Fast and Accurate Shift-Reduce Constituent Parsing

# Fast and Accurate Shift-Reduce Constituent Parsing

**Authors:** Muhua Zhu, [Yue Zhang](https://md.research.elamur.ai/free/en/authors/yue-zhang/), [Wenliang Chen](https://md.research.elamur.ai/free/en/authors/wenliang-chen/), [Min Zhang](https://md.research.elamur.ai/free/en/authors/min-zhang/), [Jingbo Zhu](https://md.research.elamur.ai/free/en/authors/jingbo-zhu/) · **Year:** 2013 · **Venue:** Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/P13-1043/) · [PDF](https://aclanthology.org/P13-1043.pdf) · [OpenAlex](https://openalex.org/W2126433015)

**Citations:** 156 citations (OpenAlex, 2026-10-14) · [91](https://md.research.elamur.ai/free/en/papers/zhu-2013-fast-accurate-shift-reduce-constituent/cited-by/) in our library, of the 140884 papers whose bibliographies we read

## Summary
Transition-based dependency parsers with beam search and global training already match chart-based parsers, but shift-reduce constituent parsers have trailed the state-of-the-art. The authors trace much of this gap to unary nodes. Because of them, competing candidate trees for one sentence need different numbers of actions, which makes their summed feature scores hard to compare during beam search and perceptron training with early update.

Their fix adds a single IDLE action. A finished state can keep applying it, which pads shorter action sequences to the length of longer ones. Starting from the Zhang and Clark (2009) parser, they also add new non-local features. They then add semi-supervised features from unlabeled data: Brown word clusters, lexical dependencies, and a dependency language model.

Evaluated on both the English and Chinese Penn treebanks, the supervised parser beats the Berkeley parser in both accuracy and speed. The semi-supervised version reaches 91.3% F-score on English and 85.6% on Chinese, the best reported CTB result at the time. Overall, the work shows that a linear-time parser can be both fast and highly accurate.

## Key points
- The baseline is the Zhang and Clark (2009) shift-reduce parser, which uses averaged perceptron training, early update, and beam search. Its feature set was made language-independent by removing Chinese-specific features.
- A sentence of n words needs between 2n and 4n actions when at most 2 consecutive unary actions are allowed. The IDLE action removes this size mismatch between candidates.
- Speed is over 89 sentences per second, roughly 14 times faster than the Berkeley parser. The authors report it as the fastest phrase-structure parser they knew of.
- Semi-supervised features add +0.9% F-score on English and +2.4% on Chinese, giving final scores of 91.3% (English) and 85.6% (CTB).
- Error analysis on the English test set shows the largest phrase-type gains for ADJP (+3.0) and SBAR (+2.5). QP slightly drops (−0.2). The parser is released as open source in ZPar version 0.6.

## Interesting ideas
- **Pad hypotheses to equal length with a no-op action.** When beam candidates are scored by summing per-step scores, a dummy action that leaves the state unchanged makes candidates of different lengths comparable. This could help any structured predictor whose outputs vary in length, such as transition-based AMR or semantic graph parsing.
- **Inspect the transition system, not just the features.** The authors located the accuracy gap in a structural property of the search: uneven sequence lengths that interact with early-update training. Checking how decoding and learning interact is a cheap diagnostic before building bigger models.
- **Bring signals from unlabeled text into the parser.** Brown clusters, auto-parsed lexical dependencies, and a dependency language model were all turned into features for a transition-based parser. This is a practical route for lower-resource languages with plenty of raw text, such as Ukrainian.
- **Break errors down along several dimensions.** The evaluation splits accuracy by phrase type, span length, sentence length, and number of unknown words. This showed that padding mainly helps long spans, while the semi-supervised features mainly help sentences with many unknown words.
- **Flag unreliable data points.** The authors explicitly discount results from tiny bins, such as only 8 sentences of length 60–70. This is a good habit for any breakdown-style evaluation.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

Topics: [Syntax & grammar formalisms](https://md.research.elamur.ai/free/en/topics/syntax-grammar/)

## Institutions

- [Agency for Science, Technology and Research](https://md.research.elamur.ai/free/en/government/agency-for-science-technology-and-research/) — Government body, Singapore, Singapore · 14 works · 13 477 citations
- [Singapore University of Technology and Design](https://md.research.elamur.ai/free/en/universities/singapore-university-of-technology-and-design/) — University, Singapore, Singapore · 20 works · 8 193 citations
- [Northeastern University](https://md.research.elamur.ai/free/en/universities/northeastern-university/) — University, Boston, United States · 23 works · 5 414 citations
- [Northeastern University](https://md.research.elamur.ai/free/en/universities/northeastern-university-cn/) — University, Shenyang, China · 5 works · 1 800 citations

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhu2013fast,
  title = {{Fast and Accurate Shift-Reduce Constituent Parsing}},
  author = {Zhu, Muhua and Zhang, Yue and Chen, Wenliang and Zhang, Min and Zhu, Jingbo},
  booktitle = {Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2013},
  doi = {10.13140/2.1.2791.2961},
  url = {https://doi.org/10.13140/2.1.2791.2961}
}
```

- [← previous Recurrent Convolutional Neural Networks for Discourse Compositionality](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2013-recurrent-convolutional-neural-networks-discourse/)
- [next → Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologically Rich Languages](https://md.research.elamur.ai/free/en/papers/seddah-2013-overview-spmrl-2013-shared-task/)
- [↑ back to papers of 2013](https://md.research.elamur.ai/free/en/papers/2013/)

## References

36 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Daniel M. Bikel. 2004. On the parameter space of generative lexicalized statistical parsing models. Ph.D. thesis, University of Pennsylvania. [find](https://scholar.google.com/scholar?q=Daniel+M%2E+Bikel%2E+2004%2E+On+the+parameter+space+of+generative+lexicalized+statistical+parsing+models%2E+Ph%2ED%2E+thesis%2C+University+of+Pennsylvania%2E)
2. Bernd Bohnet and Joakim Nivre. 2012. A transition-based system for joint part-of-speech tagging and labeled non-projective dependency parsing. In Proceedings of EMNLP, pages 12–14, Jeju Island, Korea. [find](https://scholar.google.com/scholar?q=Bernd+Bohnet+and+Joakim+Nivre%2E+2012%2E+A+transition%2Dbased+system+for+joint+part%2Dof%2Dspeech+tagging+and+labeled+non%2Dprojective+dependency+parsing%2E+In+Proceedings+of+EMNLP%2C+pages+12%E2%80%9314%2C+Jeju+Island%2C+Korea%2E) [our card](https://md.research.elamur.ai/free/en/papers/bohnet-2012-transition-based-system-joint-part/)
3. Xavier Carreras, Michael Collins, and Terry Koo. 2008. Tag, dynamic programming, and the perceptron for efficient, feature-rich parsing. In Proceedings of CoNLL, pages 9–16, Manchester, England. [find](https://scholar.google.com/scholar?q=Xavier+Carreras%2C+Michael+Collins%2C+and+Terry+Koo%2E+2008%2E+Tag%2C+dynamic+programming%2C+and+the+perceptron+for+efficient%2C+feature%2Drich+parsing%2E+In+Proceedings+of+CoNLL%2C+pages+9%E2%80%9316%2C+Manchester%2C+England%2E)
4. PP 88.1 87.9 89.3 +1.2 SBAR 85.7 86.6 88.2 +2.5 ADVP 84.6 84.5 86.8 +2.2 ADJP 72.1 73.6 75.1 +3.0 WHNP 94.8 95.5 95.7 +0.9 QP 89.3 88.6 89.1 -0.2 90 . 68 90 . 35 90 . 24 89 . 88 88 . 66 87 . 99 87 . 96 87 . 33 86 . 39 85 . 95 83 . 89 82 . 74 80 . 49 83 . 7 81 . 42 Extended Semi-supervised Eugune Cha… [find](https://scholar.google.com/scholar?q=PP+88%2E1+87%2E9+89%2E3+%2B1%2E2+SBAR+85%2E7+86%2E6+88%2E2+%2B2%2E5+ADVP+84%2E6+84%2E5+86%2E8+%2B2%2E2+ADJP+72%2E1+73%2E6+75%2E1+%2B3%2E0+WHNP+94%2E8+95%2E5+95%2E7+%2B0%2E9+QP+89%2E3+88%2E6+89%2E1+%2D0%2E2+90+%2E+68+90+%2E+35+90+%2E+24+89+%2E+88+88+%2E+66+87+%2E+99+87+%2E+9) [our card](https://md.research.elamur.ai/free/en/papers/narrative-2005-charniak-coarse-fine-n-best-parsing/)
5. Eugune Charniak. 2000. A maximum-entropy-inspired parser. In Proceedings of NAACL, pages 132–139, Seattle, Washington, USA. [find](https://scholar.google.com/scholar?q=Eugune+Charniak%2E+2000%2E+A+maximum%2Dentropy%2Dinspired+parser%2E+In+Proceedings+of+NAACL%2C+pages+132%E2%80%93139%2C+Seattle%2C+Washington%2C+USA%2E) [our card](https://md.research.elamur.ai/free/en/papers/charniak-2000-maximum-entropy-inspired-parser/)
6. Wenliang Chen, Junichi Kazama, Kiyotaka Uchimoto, and Kentaro Torisawa. 2009. Improving dependency parsing with subtrees from auto-parsed data. In Proceedings of EMNLP, pages 570–579, Singapore. [find](https://scholar.google.com/scholar?q=Wenliang+Chen%2C+Junichi+Kazama%2C+Kiyotaka+Uchimoto%2C+and+Kentaro+Torisawa%2E+2009%2E+Improving+dependency+parsing+with+subtrees+from+auto%2Dparsed+data%2E+In+Proceedings+of+EMNLP%2C+pages+570%E2%80%93579%2C+Singapore%2E)
7. Wenliang Chen, Min Zhang, and Haizhou Li. 2012. Utilizing dependency language models for graph-based dependency. In Proceedings of ACL, pages 213–222, Jeju, Republic of Korea. [find](https://scholar.google.com/scholar?q=Wenliang+Chen%2C+Min+Zhang%2C+and+Haizhou+Li%2E+2012%2E+Utilizing+dependency+language+models+for+graph%2Dbased+dependency%2E+In+Proceedings+of+ACL%2C+pages+213%E2%80%93222%2C+Jeju%2C+Republic+of+Korea%2E)
8. Michael Collins and Brian Roark. 2004. Incremental parsing with the perceptron algorithm. In Proceedings of ACL, Stroudsburg, PA, USA. [find](https://scholar.google.com/scholar?q=Michael+Collins+and+Brian+Roark%2E+2004%2E+Incremental+parsing+with+the+perceptron+algorithm%2E+In+Proceedings+of+ACL%2C+Stroudsburg%2C+PA%2C+USA%2E) [our card](https://md.research.elamur.ai/free/en/papers/collins-2004-incremental-parsing-perceptron-algorithm/)
9. Michael Collins. 1997. Three generative, lexicalised models for statistical parsing. In Proceedings of ACL, Madrid, Spain. [find](https://scholar.google.com/scholar?q=Michael+Collins%2E+1997%2E+Three+generative%2C+lexicalised+models+for+statistical+parsing%2E+In+Proceedings+of+ACL%2C+Madrid%2C+Spain%2E) [our card](https://md.research.elamur.ai/free/en/papers/collins-1997-three-generative-lexicalised-models-statistical/)
10. Michael Collins. 1999. Head-driven statistical models for natural language parsing. Ph.D. thesis, University of Pennsylvania. [find](https://scholar.google.com/scholar?q=Michael+Collins%2E+1999%2E+Head%2Ddriven+statistical+models+for+natural+language+parsing%2E+Ph%2ED%2E+thesis%2C+University+of+Pennsylvania%2E)
11. Michael Collins. 2000. Discriminative reranking for natural language processing. In Proceedings of ICML, pages 175–182, Stanford, CA, USA. [find](https://scholar.google.com/scholar?q=Michael+Collins%2E+2000%2E+Discriminative+reranking+for+natural+language+processing%2E+In+Proceedings+of+ICML%2C+pages+175%E2%80%93182%2C+Stanford%2C+CA%2C+USA%2E)
12. Hal Daume III. 2006. Practical Structured Learning for Natural Language Processing. Ph.D. thesis, USC. [find](https://scholar.google.com/scholar?q=Hal+Daume+III%2E+2006%2E+Practical+Structured+Learning+for+Natural+Language+Processing%2E+Ph%2ED%2E+thesis%2C+USC%2E)
13. Zhongqiang Huang and Mary Harper. 2009. Self-training PCFG grammars with latent annotations across languages. In Proceedings of EMNLP, pages 832–841, Singapore. [find](https://scholar.google.com/scholar?q=Zhongqiang+Huang+and+Mary+Harper%2E+2009%2E+Self%2Dtraining+PCFG+grammars+with+latent+annotations+across+languages%2E+In+Proceedings+of+EMNLP%2C+pages+832%E2%80%93841%2C+Singapore%2E)
14. Liang Huang and Kenji Sagae. 2010. Dynamic programming for linear-time incremental parsing. In Proceedings of ACL, pages 1077–1086, Uppsala, Sweden. [find](https://scholar.google.com/scholar?q=Liang+Huang+and+Kenji+Sagae%2E+2010%2E+Dynamic+programming+for+linear%2Dtime+incremental+parsing%2E+In+Proceedings+of+ACL%2C+pages+1077%E2%80%931086%2C+Uppsala%2C+Sweden%2E)
15. Zhongqiang Huang, Mary Harper, and Slav Petrov. 2010. Self-training with products of latent variable grammars. In Proceedings of EMNLP, pages 12–22, Massachusetts, USA. [find](https://scholar.google.com/scholar?q=Zhongqiang+Huang%2C+Mary+Harper%2C+and+Slav+Petrov%2E+2010%2E+Self%2Dtraining+with+products+of+latent+variable+grammars%2E+In+Proceedings+of+EMNLP%2C+pages+12%E2%80%9322%2C+Massachusetts%2C+USA%2E)
16. Liang Huang. 2008. Forest reranking: discriminative parsing with non-local features. In Proceedings of ACL, pages 586–594, Ohio, USA. [find](https://scholar.google.com/scholar?q=Liang+Huang%2E+2008%2E+Forest+reranking%3A+discriminative+parsing+with+non%2Dlocal+features%2E+In+Proceedings+of+ACL%2C+pages+586%E2%80%93594%2C+Ohio%2C+USA%2E)
17. Liang-Ya Huang. 2009. Improve Chinese parsing with Max-Ent reranking parser. In Master Project Report, Brown University. [find](https://scholar.google.com/scholar?q=Liang%2DYa+Huang%2E+2009%2E+Improve+Chinese+parsing+with+Max%2DEnt+reranking+parser%2E+In+Master+Project+Report%2C+Brown+University%2E)
18. Terry Koo, Xavier Carreras, and Michael Collins. 2008. Simple semi-supervised dependency parsing. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Terry+Koo%2C+Xavier+Carreras%2C+and+Michael+Collins%2E+2008%2E+Simple+semi%2Dsupervised+dependency+parsing%2E+In+Proceedings+of+ACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/koo-2008-simple-semi-supervised-dependency-parsing/)
19. J. Lafferty, A. McCallum, and F. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of ICML, pages 282–289, Massachusetts, USA, June. [find](https://scholar.google.com/scholar?q=J%2E+Lafferty%2C+A%2E+McCallum%2C+and+F%2E+Pereira%2E+2001%2E+Conditional+random+fields%3A+Probabilistic+models+for+segmenting+and+labeling+sequence+data%2E+In+Proceedings+of+ICML%2C+pages+282%E2%80%93289%2C+Massachusetts%2C+USA%2C+Ju)
20. Percy Liang. 2005. Semi-supervised learning for natural language. Master’s thesis, Massachusetts Institute of Technology. [find](https://scholar.google.com/scholar?q=Percy+Liang%2E+2005%2E+Semi%2Dsupervised+learning+for+natural+language%2E+Master%E2%80%99s+thesis%2C+Massachusetts+Institute+of+Technology%2E)
21. Mitchell P. Marcus, Beatrice Santorini, and Mary A. Marcinkiewiz. 1993. Building a large annotated corpus of English. Computational Linguistics, 19(2):313–330. [find](https://scholar.google.com/scholar?q=Mitchell+P%2E+Marcus%2C+Beatrice+Santorini%2C+and+Mary+A%2E+Marcinkiewiz%2E+1993%2E+Building+a+large+annotated+corpus+of+English%2E+Computational+Linguistics%2C+19%282%29%3A313%E2%80%93330%2E)
22. David McClosky, Eugene Charniak, and Mark Johnson. 2006. Effective self-training for parsing. In Proceedings of the HLT/NAACL, Main Conference, pages 152–159, New York City, USA, June. [find](https://scholar.google.com/scholar?q=David+McClosky%2C+Eugene+Charniak%2C+and+Mark+Johnson%2E+2006%2E+Effective+self%2Dtraining+for+parsing%2E+In+Proceedings+of+the+HLT%2FNAACL%2C+Main+Conference%2C+pages+152%E2%80%93159%2C+New+York+City%2C+USA%2C+June%2E) [our card](https://md.research.elamur.ai/free/en/papers/aclbulk-2006-mcclosky-effective-self-training-parsing/)
23. Ryan McDonald, Koby Crammer, and Fernando Pereira. 2005. Online large-margin training of dependency parsers. In Proceedings of ACL, pages 91– 98, Ann Arbor, Michigan, June. [find](https://scholar.google.com/scholar?q=Ryan+McDonald%2C+Koby+Crammer%2C+and+Fernando+Pereira%2E+2005%2E+Online+large%2Dmargin+training+of+dependency+parsers%2E+In+Proceedings+of+ACL%2C+pages+91%E2%80%93+98%2C+Ann+Arbor%2C+Michigan%2C+June%2E) [our card](https://md.research.elamur.ai/free/en/papers/narrative-2005-mcdonald-online-large-margin-training-dependency/)
24. Joakim Nivre, Johan Hall, and Jens Nilsson. 2006. Maltparser: a data-driven parser-generator for dependency parsing. In Proceedings of LREC, pages 2216–2219. [find](https://scholar.google.com/scholar?q=Joakim+Nivre%2C+Johan+Hall%2C+and+Jens+Nilsson%2E+2006%2E+Maltparser%3A+a+data%2Ddriven+parser%2Dgenerator+for+dependency+parsing%2E+In+Proceedings+of+LREC%2C+pages+2216%E2%80%932219%2E) [our card](https://md.research.elamur.ai/free/en/papers/nivre-2006-maltparser-data-driven-parser-generator/)
25. Slav Petrov and Dan Klein. 2007. Improved inference for unlexicalized parsing. In Proceedings of HLT/NAACL, pages 404–411, Rochester, New York, April. [find](https://scholar.google.com/scholar?q=Slav+Petrov+and+Dan+Klein%2E+2007%2E+Improved+inference+for+unlexicalized+parsing%2E+In+Proceedings+of+HLT%2FNAACL%2C+pages+404%E2%80%93411%2C+Rochester%2C+New+York%2C+April%2E) [our card](https://md.research.elamur.ai/free/en/papers/petrov-2007-improved-inference-unlexicalized-parsing/)
26. Adwait Ratnaparkhi. 1997. A linear observed time statistical parser based on maximum entropy models. In Proceedings of EMNLP, Rhode Island, USA. [find](https://scholar.google.com/scholar?q=Adwait+Ratnaparkhi%2E+1997%2E+A+linear+observed+time+statistical+parser+based+on+maximum+entropy+models%2E+In+Proceedings+of+EMNLP%2C+Rhode+Island%2C+USA%2E)
27. Kenji Sagae and Alon Lavie. 2005. A classifier-based parser with linear run-time complexity. In Proceedings of IWPT, pages 125–132, Vancouver, Canada. [find](https://scholar.google.com/scholar?q=Kenji+Sagae+and+Alon+Lavie%2E+2005%2E+A+classifier%2Dbased+parser+with+linear+run%2Dtime+complexity%2E+In+Proceedings+of+IWPT%2C+pages+125%E2%80%93132%2C+Vancouver%2C+Canada%2E) [our card](https://md.research.elamur.ai/free/en/papers/sagae-2005-classifier-based-parser-linear-run/)
28. Kenji Sagae and Alon Lavie. 2006. Parser combination by reparsing. In Proceedings of HLT/NAACL, Companion Volume: Short Papers, pages 129–132, New York, USA. [find](https://scholar.google.com/scholar?q=Kenji+Sagae+and+Alon+Lavie%2E+2006%2E+Parser+combination+by+reparsing%2E+In+Proceedings+of+HLT%2FNAACL%2C+Companion+Volume%3A+Short+Papers%2C+pages+129%E2%80%93132%2C+New+York%2C+USA%2E) [our card](https://md.research.elamur.ai/free/en/papers/sagae-2006-parser-combination-reparsing/)
29. Libin Shen, Jinxi Xu, and Ralph Weischedel. 2008. A new string-to-dependency machine translation algorithm with a target dependency language model. In Proceedings of ACL, pages 577–585, Ohio, USA. [find](https://scholar.google.com/scholar?q=Libin+Shen%2C+Jinxi+Xu%2C+and+Ralph+Weischedel%2E+2008%2E+A+new+string%2Dto%2Ddependency+machine+translation+algorithm+with+a+target+dependency+language+model%2E+In+Proceedings+of+ACL%2C+pages+577%E2%80%93585%2C+Ohio%2C+USA%2E) [our card](https://md.research.elamur.ai/free/en/papers/shen-2008-new-string-dependency-machine-translation/)
30. Weiwei Sun and Hans Uszkoreit. 2012. Capturing paradigmatic and syntagmatic lexical relations: towards accurate Chinese part-of-speech tagging. In Proceedings of ACL, Jeju, Republic of Korea. [find](https://scholar.google.com/scholar?q=Weiwei+Sun+and+Hans+Uszkoreit%2E+2012%2E+Capturing+paradigmatic+and+syntagmatic+lexical+relations%3A+towards+accurate+Chinese+part%2Dof%2Dspeech+tagging%2E+In+Proceedings+of+ACL%2C+Jeju%2C+Republic+of+Korea%2E)
31. Nianwen Xue, Fei Xia, Fu dong Chiou, and Martha Palmer. 2005. The Penn Chinese Treebank: phrase structure annotation of a large corpus. Natural Language Engineering, 11(2):207–238. [find](https://scholar.google.com/scholar?q=Nianwen+Xue%2C+Fei+Xia%2C+Fu+dong+Chiou%2C+and+Martha+Palmer%2E+2005%2E+The+Penn+Chinese+Treebank%3A+phrase+structure+annotation+of+a+large+corpus%2E+Natural+Language+Engineering%2C+11%282%29%3A207%E2%80%93238%2E)
32. Hiroyasu Yamada and Yuji Matsumoto. 2003. Statistical dependency analysis with support vector machines. In Proceedings of IWPT, pages 195–206, Nancy, France. [find](https://scholar.google.com/scholar?q=Hiroyasu+Yamada+and+Yuji+Matsumoto%2E+2003%2E+Statistical+dependency+analysis+with+support+vector+machines%2E+In+Proceedings+of+IWPT%2C+pages+195%E2%80%93206%2C+Nancy%2C+France%2E) [our card](https://md.research.elamur.ai/free/en/papers/parsers-2003-yamada-statistical-dependency-analysis-support-vector/)
33. Yue Zhang and Stephen Clark. 2008. Joint word segmentation and POS tagging using a single perceptron. In Proceedings of ACL/HLT, pages 888–896, Columbus, Ohio. [find](https://scholar.google.com/scholar?q=Yue+Zhang+and+Stephen+Clark%2E+2008%2E+Joint+word+segmentation+and+POS+tagging+using+a+single+perceptron%2E+In+Proceedings+of+ACL%2FHLT%2C+pages+888%E2%80%93896%2C+Columbus%2C+Ohio%2E)
34. Yue Zhang and Stephen Clark. 2009. Transition-based parsing of the Chinese Treebank using a global discriminative model. In Proceedings of IWPT, Paris, France, October. [find](https://scholar.google.com/scholar?q=Yue+Zhang+and+Stephen+Clark%2E+2009%2E+Transition%2Dbased+parsing+of+the+Chinese+Treebank+using+a+global+discriminative+model%2E+In+Proceedings+of+IWPT%2C+Paris%2C+France%2C+October%2E) [our card](https://md.research.elamur.ai/free/en/papers/zhang-2009-transition-based-parsing-chinese-treebank/)
35. Yue Zhang and Joakim Nivre. 2011. Transition-based dependency parsing with rich non-local features. In Proceedings of ACL, pages 188–193, Portland, Oregon, USA. [find](https://scholar.google.com/scholar?q=Yue+Zhang+and+Joakim+Nivre%2E+2011%2E+Transition%2Dbased+dependency+parsing+with+rich+non%2Dlocal+features%2E+In+Proceedings+of+ACL%2C+pages+188%E2%80%93193%2C+Portland%2C+Oregon%2C+USA%2E)
36. Muhua Zhu, Jingbo Zhu, and Huizhen Wang. 2012. Exploiting lexical dependencies from large-scale data for better shift-reduce constituency parsing. In Proceedings of COLING, pages 3171–3186, Mumbai, India. [find](https://scholar.google.com/scholar?q=Muhua+Zhu%2C+Jingbo+Zhu%2C+and+Huizhen+Wang%2E+2012%2E+Exploiting+lexical+dependencies+from+large%2Dscale+data+for+better+shift%2Dreduce+constituency+parsing%2E+In+Proceedings+of+COLING%2C+pages+3171%E2%80%933186%2C+Mumbai%2C+In)