---
title: "Joint Incremental Disfluency Detection and Dependency Parsing"
description: "Unscripted speech is full of self-corrections and fillers, which make transcripts hard to read… 88.6 UAS. 33 references, cited by 45 papers here."
authors: ["Matthew Honnibal", "Mark Johnson"]
year: 2014
venue: "Transactions of the Association for Computational Linguistics"
source: "https://aclanthology.org/Q14-1011/"
doi: "10.1162/tacl_a_00171"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/honnibal-2014-joint-incremental-disfluency-detection-dependency/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/honnibal-2014-joint-incremental-disfluency-detection-dependency/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2014](https://md.research.elamur.ai/free/en/papers/2014/page/2/) / Joint Incremental Disfluency Detection and Dependency Parsing

# Joint Incremental Disfluency Detection and Dependency Parsing

**Authors:** [Matthew Honnibal](https://md.research.elamur.ai/free/en/authors/matthew-honnibal/) and [Mark Johnson](https://md.research.elamur.ai/free/en/authors/mark-johnson/) · **Year:** 2014 · **Venue:** [Transactions of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/tacl/) ([Transactions of the Association for Computational Linguistics (TACL) 2014](https://md.research.elamur.ai/free/en/venues/tacl/2014/)) · **Publisher:** [The MIT Press](https://md.research.elamur.ai/free/en/publishers/the-mit-press/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/Q14-1011/) · [PDF](https://aclanthology.org/Q14-1011.pdf) · [DOI 10.1162/tacl\_a\_00171](https://doi.org/10.1162/tacl_a_00171) · [OpenAlex](https://openalex.org/W2203858612)

**Citations:** 101 citations (OpenAlex, 2026-10-14) · [45](https://md.research.elamur.ai/free/en/papers/honnibal-2014-joint-incremental-disfluency-detection-dependency/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Unscripted speech is full of self-corrections and fillers, which make transcripts hard to read and confuse parsers built for written text. Honnibal and Johnson handle disfluency detection and dependency parsing as one incremental task, rather than running a separate detector before the parser. Their system is a transition-based parser with beam search and a structured averaged perceptron, following Zhang and Clark (2011). It is trained on the Switchboard portion of the Penn Treebank, converted to Stanford Basic Dependencies. The main innovation is Edit, a non-monotonic action added to the arc-eager system. Edit marks the word on top of the stack, plus its rightward descendants, as disfluent and removes their arcs. It then pushes that word's former left children back onto the stack so they can be analysed again. New features also capture the "rough copy" shape typical of repairs. The joint model was compared with two pipelines that feed leading disfluency detectors into the same parser. It beat both pipelines on parsing and on repair detection, while staying fast and incremental. This makes it promising for unsegmented speech-recognition output.

## Key points
- **Results:** the joint model reaches 90.5% unlabelled attachment score and 84.0% on speech-repair detection. It processes more than 550 tokens per second, with expected linear runtime. The code is released as open source (redshift on GitHub).
- **Training data:** only 619,236 of the 1,482,845 Switchboard disfluency-training tokens (DPS files) have gold syntactic trees (MRG files). Even so, the system surpasses Qian and Liu (2013) while using under half the data.
- **Preprocessing:**
  - Dependencies come from the Stanford converter (2013-04-05 version), which proved robust to disfluent material: 99.54% of unlabelled dependencies were unchanged.
  - "um" and "uh" tokens are dropped.
  - "you know" and "i mean" are merged into single tokens.
- **Edit behaviour on development data:**
  - The parser applied 2,558 Edits, which flagged 2,706 words; 2,495 of these were correct.
  - Edits returned 1,132 left children to the stack. Of these, 547 were later marked disfluent (500 correctly).
- **Related systems (not directly comparable):** Rasooli and Tetreault (2013), a greedy joint parser, reported 88.6 UAS and 81.4% disfluency F-measure. The earlier best incremental detector (Zwarts et al., 2010) reached about 77%.

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

## Institutions

- [Macquarie University](https://md.research.elamur.ai/free/en/universities/macquarie-university/) — University, Sydney, Australia · 17 works · 4,827 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (1): [🌳 Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) · 120 works

## Cite

Cite as: Matthew Honnibal and Mark Johnson. 2014. Joint Incremental Disfluency Detection and Dependency Parsing. Transactions of the Association for Computational Linguistics.

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

```bibtex
@article{honnibal2014joint,
  title = {{Joint Incremental Disfluency Detection and Dependency Parsing}},
  author = {Matthew Honnibal and Mark Johnson},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2014},
  doi = {10.1162/tacl\_a\_00171},
  url = {https://doi.org/10.1162/tacl_a_00171}
}
```

- [← previous NaturalLI: Natural Logic Inference for Common Sense Reasoning](https://md.research.elamur.ai/free/en/papers/angeli-2014-naturalli-natural-logic-inference-common/)
- [next → Lexicon Infused Phrase Embeddings for Named Entity Resolution](https://md.research.elamur.ai/free/en/papers/passos-2014-lexicon-infused-phrase-embeddings-named/)
- [↑ back to papers of 2014](https://md.research.elamur.ai/free/en/papers/2014/page/2/)

## References

33 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Miguel Ballesteros and Joakim Nivre. 2013. Going to the roots of dependency parsing. Computational Linguistics. 39:1. [find](https://scholar.google.com/scholar?q=Miguel+Ballesteros+and+Joakim+Nivre%2E+2013%2E+Going+to+the+roots+of+dependency+parsing%2E+Computational+Linguistics%2E+39%3A1%2E)
2. Peter F. Brown, Peter V. deSouza, Robert L. Mercer, Vincent J. Della Pietra, and Jenifer C. Lai. 1992. Class-based n-gram models of natural language. Computational Linguistics, 18:467– 479. transition system for dependency parsing. In Proceedings of the Seventeenth Conference on Computational Natura… [find](https://scholar.google.com/scholar?q=Peter+F%2E+Brown%2C+Peter+V%2E+deSouza%2C+Robert+L%2E+Mercer%2C+Vincent+J%2E+Della+Pietra%2C+and+Jenifer+C%2E+Lai%2E+1992%2E+Class%2Dbased+n%2Dgram+models+of+natural+language%2E+Computational+Linguistics%2C+18%3A467%E2%80%93+479%2E+transition)
3. Eugene Charniak. 2001. [Immediate-head parsing for language models](https://md.research.elamur.ai/free/en/papers/charniak-2001-immediate-head-parsing-language-models/). In Proceedings of 39th Annual Meeting of the Association for Computational Linguistics, pages 124–131. Association for Computational Linguistics, Toulouse, France.
4. Liang Huang, Suphan Fayong, and Yang Guo. 2012. [Structured perceptron with inexact search](https://md.research.elamur.ai/free/en/papers/huang-2012-structured-perceptron-inexact-search/). In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 142– 151. Association for Computational Linguistics, Mon…
5. Eugene Charniak and Mark Johnson. 2001. [Edit detection and parsing for transcribed speech](https://md.research.elamur.ai/free/en/papers/charniak-2001-edit-detection-parsing-transcribed-speech/). In Proceedings of the 2nd Meeting of the North American Chapter of the Association for Computational Linguistics, pages 118–126. The Association for Computational Linguistics.
6. Eugene Charniak and Mark Johnson. 2005. [Coarse-to-fine n-best parsing and MaxEnt discriminative reranking](https://md.research.elamur.ai/free/en/papers/charniak-2005-coarse-fine-n-best-parsing/). In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, pages 173–180. Association for Computational Linguistics, Ann Arbor, Michigan.
7. Michael Collins. 2002. [Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms](https://md.research.elamur.ai/free/en/papers/collins-2002-discriminative-training-methods-hidden-markov/). In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, pages 1–8. Association for Computational Linguistics.
8. Marie-Catherine de Marneffe, Bill MacCartney, and Christopher D. Manning. 2006. [Generating typed dependency parses from phrase structure parses](https://md.research.elamur.ai/free/en/papers/marneffe-2006-generating-typed-dependency-parses-phrase/). In Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC).
9. Lyn Frazier and Keith Rayner. 1982. Making and correcting errors during sentence comprehension: Eye movements in the analysis of structurally ambiguous sentences. Cognitive Psychology, 14(2):178–210. [find](https://scholar.google.com/scholar?q=Lyn+Frazier+and+Keith+Rayner%2E+1982%2E+Making+and+correcting+errors+during+sentence+comprehension%3A+Eye+movements+in+the+analysis+of+structurally+ambiguous+sentences%2E+Cognitive+Psychology%2C+14%282%29%3A178%E2%80%93210%2E)
10. Yoav Goldberg and Joakim Nivre. 2012. A dynamic oracle for arc-eager dependency parsing. In Proceedings of the 24th International Conference on Computational Linguistics (Coling 2012). Association for Computational Linguistics, Mumbai, India. [find](https://scholar.google.com/scholar?q=Yoav+Goldberg+and+Joakim+Nivre%2E+2012%2E+A+dynamic+oracle+for+arc%2Deager+dependency+parsing%2E+In+Proceedings+of+the+24th+International+Conference+on+Computational+Linguistics+%28Coling+2012%29%2E+Association+for)
11. Matthew Honnibal, Yoav Goldberg, and Mark Johnson. 2013. [A non-monotonic arc-eager Mark Johnson and Eugene Charniak](https://md.research.elamur.ai/free/en/papers/johnson-2004-tag-based-noisy-channel-model/). 2004. A TAG-based noisy channel model of speech repairs. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, pages 33–39.
12. Douglas A. Jones, Florian Wolf, Edward Gibson, Elliott Williams, Evelina Fedorenko, Douglas A. Reynolds, and Marc A. Zissman. 2003. Measuring the readability of automatic speech-to-text transcripts. In INTERSPEECH. ISCA. [find](https://scholar.google.com/scholar?q=Douglas+A%2E+Jones%2C+Florian+Wolf%2C+Edward+Gibson%2C+Elliott+Williams%2C+Evelina+Fedorenko%2C+Douglas+A%2E+Reynolds%2C+and+Marc+A%2E+Zissman%2E+2003%2E+Measuring+the+readability+of+automatic+speech%2Dto%2Dtext+transcripts%2E+I)
13. Fredrik Jorgensen. 2007. The effects of disfluency detection in parsing spoken language. In Joakim Nivre, Heiki-Jaan Kaalep, Kadri Muischnek, and Mare Koit, editors, Proceedings of the 16th Nordic Conference of Computational Linguistics NODALIDA-2007, pages 240–244. [find](https://scholar.google.com/scholar?q=Fredrik+Jorgensen%2E+2007%2E+The+effects+of+disfluency+detection+in+parsing+spoken+language%2E+In+Joakim+Nivre%2C+Heiki%2DJaan+Kaalep%2C+Kadri+Muischnek%2C+and+Mare+Koit%2C+editors%2C+Proceedings+of+the+16th+Nordic+Con)
14. Terry Koo and Michael Collins. 2010. Efficient third-order dependency parsers. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL), pages 1– 11. [find](https://scholar.google.com/scholar?q=Terry+Koo+and+Michael+Collins%2E+2010%2E+Efficient+third%2Dorder+dependency+parsers%2E+In+Proceedings+of+the+48th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28ACL%29%2C+pages+1%E2%80%93+11%2E)
15. Percy Liang. 2005. Semi-supervised learning for natural language. Ph.D. thesis, MIT. [find](https://scholar.google.com/scholar?q=Percy+Liang%2E+2005%2E+Semi%2Dsupervised+learning+for+natural+language%2E+Ph%2ED%2E+thesis%2C+MIT%2E)
16. Christopher D. Manning. 2011. Part-of-speech tagging from 97linguistics? In Proceedings of the 12th international conference on Computational linguistics and intelligent text processing - Volume Part I, CICLing’11, pages 171–189. Springer-Verlag, Berlin, Heidelberg. [find](https://scholar.google.com/scholar?q=Christopher+D%2E+Manning%2E+2011%2E+Part%2Dof%2Dspeech+tagging+from+97linguistics%3F+In+Proceedings+of+the+12th+international+conference+on+Computational+linguistics+and+intelligent+text+processing+%2D+Volume+Part+)
17. Michell P. Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. [Building a large annotated corpus of English: The Penn Treebank](https://md.research.elamur.ai/free/en/papers/marcus-1993-building-large-annotated-corpus-english/). Computational Linguistics, 19(2):313–330.
18. Joakim Nivre. 2003. [An efficient algorithm for projective dependency parsing](https://md.research.elamur.ai/free/en/papers/nivre-2003-efficient-algorithm-projective-dependency-parsing/). In Proceedings of the 8th International Workshop on Parsing Technologies (IWPT), pages 149–160.
19. Joakim Nivre. 2008. [Algorithms for deterministic incremental dependency parsing](https://md.research.elamur.ai/free/en/papers/nivre-2008-algorithms-deterministic-incremental-dependency-parsing/). Computational Linguistics, 34:513–553.
20. Xian Qian and Yang Liu. 2013. Disfluency detection using multi-step stacked learning. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 820–825. Association for Computational Linguistics, Atlanta,… [find](https://scholar.google.com/scholar?q=Xian+Qian+and+Yang+Liu%2E+2013%2E+Disfluency+detection+using+multi%2Dstep+stacked+learning%2E+In+Proceedings+of+the+2013+Conference+of+the+North+American+Chapter+of+the+Association+for+Computational+Linguisti)
21. Mohammad Sadegh Rasooli and Joel Tetreault. 2013. Joint parsing and disfluency detection in linear time. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 124–129. Association for Computational Linguistics, Seattle, Washington, USA. [find](https://scholar.google.com/scholar?q=Mohammad+Sadegh+Rasooli+and+Joel+Tetreault%2E+2013%2E+Joint+parsing+and+disfluency+detection+in+linear+time%2E+In+Proceedings+of+the+2013+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+page)
22. Brian Roark, Mary Harper, Eugene Charniak, Bonnie Dorr, Mark Johnson, Jeremy Kahn, Yang Liu, Mary Ostendorf, John Hale, Anna Krasnyanskaya, Matthew Lease, Izhak Shafran, Matthew Snover, Robin Stewart, and LisaYung. 2006. Sparseval: Evaluation metrics for parsing speech. In Proceedings of Language Re… [find](https://scholar.google.com/scholar?q=Brian+Roark%2C+Mary+Harper%2C+Eugene+Charniak%2C+Bonnie+Dorr%2C+Mark+Johnson%2C+Jeremy+Kahn%2C+Yang+Liu%2C+Mary+Ostendorf%2C+John+Hale%2C+Anna+Krasnyanskaya%2C+Matthew+Lease%2C+Izhak+Shafran%2C+Matthew+Snover%2C+Robin+Stewart%2C)
23. Francesco Sartorio, Giorgio Satta, and Joakim Nivre. 2013. A transition-based dependency parser using a dynamic parsing strategy. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 135–144. Association for Computational Linguistics, Sofia, Bulgaria. [find](https://scholar.google.com/scholar?q=Francesco+Sartorio%2C+Giorgio+Satta%2C+and+Joakim+Nivre%2E+2013%2E+A+transition%2Dbased+dependency+parser+using+a+dynamic+parsing+strategy%2E+In+Proceedings+of+the+51st+Annual+Meeting+of+the+Association+for+Compu)
24. Elizabeth Shriberg. 1994. Preliminaries to a Theory of Speech Disfluencies. Ph.D. thesis, University of California, Berkeley. [find](https://scholar.google.com/scholar?q=Elizabeth+Shriberg%2E+1994%2E+Preliminaries+to+a+Theory+of+Speech+Disfluencies%2E+Ph%2ED%2E+thesis%2C+University+of+California%2C+Berkeley%2E)
25. Xu Sun, Takuya Matsuzaki, Daisuke Okanohara, and Jun’ichi Tsujii. 2009. Latent variable perceptron algorithm for structured classification. In IJCAI, pages 1236–1242. [find](https://scholar.google.com/scholar?q=Xu+Sun%2C+Takuya+Matsuzaki%2C+Daisuke+Okanohara%2C+and+Jun%E2%80%99ichi+Tsujii%2E+2009%2E+Latent+variable+perceptron+algorithm+for+structured+classification%2E+In+IJCAI%2C+pages+1236%E2%80%931242%2E)
26. Joseph Turian, Lev-Arie Ratinov, and Yoshua Bengio. 2010. [Word representations: A simple and general method for semi-supervised learning](https://md.research.elamur.ai/free/en/papers/turian-2010-word-representations-simple-general-method/). In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 384–394. Association for Computational Linguistics, Uppsala, Swe…
27. Dongdong Zhang, Shuangzhi Wu, Nan Yang, and Mu Li. 2013. Punctuation prediction with transition-based parsing. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 752–760. Association for Computational Linguistics, Sofia, Bulgaria. [find](https://scholar.google.com/scholar?q=Dongdong+Zhang%2C+Shuangzhi+Wu%2C+Nan+Yang%2C+and+Mu+Li%2E+2013%2E+Punctuation+prediction+with+transition%2Dbased+parsing%2E+In+Proceedings+of+the+51st+Annual+Meeting+of+the+Association+for+Computational+Linguistic)
28. Yue Zhang and Stephen Clark. 2011. Syntactic processing using the generalized perceptron and beam search. Computational Linguistics, 37(1):105–151. [find](https://scholar.google.com/scholar?q=Yue+Zhang+and+Stephen+Clark%2E+2011%2E+Syntactic+processing+using+the+generalized+perceptron+and+beam+search%2E+Computational+Linguistics%2C+37%281%29%3A105%E2%80%93151%2E)
29. Yue Zhang and Joakim Nivre. 2011. Transition-based dependency parsing with rich non-local features. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 188–193. Association for Computational Linguistics, Portland, 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+the+49th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%3A+Human+La)
30. Muhua Zhu, Yue Zhang, Wenliang Chen, Min Zhang, and Jingbo Zhu. 2013. [Fast and accurate shift-reduce constituent parsing](https://md.research.elamur.ai/free/en/papers/zhu-2013-fast-accurate-shift-reduce-constituent/). In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 434–443. Association for Computational Linguistics, Sofia, Bulgaria.
31. Simon Zwarts and Mark Johnson. 2011. The impact of language models and loss functions on repair disfluency detection. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 703–711. Association for Computational Linguistics, Por… [find](https://scholar.google.com/scholar?q=Simon+Zwarts+and+Mark+Johnson%2E+2011%2E+The+impact+of+language+models+and+loss+functions+on+repair+disfluency+detection%2E+In+Proceedings+of+the+49th+Annual+Meeting+of+the+Association+for+Computational+Lin)
32. Simon Zwarts, Mark Johnson, and Robert Dale. 2010. Detecting speech repairs incrementally using a noisy channel approach. In Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pages 1371–1378. [find](https://scholar.google.com/scholar?q=Simon+Zwarts%2C+Mark+Johnson%2C+and+Robert+Dale%2E+2010%2E+Detecting+speech+repairs+incrementally+using+a+noisy+channel+approach%2E+In+Proceedings+of+the+23rd+International+Conference+on+Computational+Linguisti)
33. Coling 2010 Organizing Committee, Beijing, China. [find](https://scholar.google.com/scholar?q=Coling+2010+Organizing+Committee%2C+Beijing%2C+China%2E)

*Updated 24 October 2026*