--- title: "Learning Accurate, Compact, and Interpretable Tree Annotation — Petrov 2006" description: "Hand-made tree annotations, which split a category such as NP into subject and object NPs, raise parser accuracy… 19 references, cited by 453 papers here." authors: ["Slav Petrov", "Leon Barrett", "Romain Thibaux", "Dan Klein"] year: 2006 venue: "Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics" source: "https://aclanthology.org/P06-1055/" doi: "10.3115/1220175.1220230" 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/petrov-2006-learning-accurate-compact-interpretable-tree/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/petrov-2006-learning-accurate-compact-interpretable-tree/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2006](https://md.research.elamur.ai/free/en/papers/2006/) / Learning Accurate, Compact, and Interpretable Tree Annotation # Learning Accurate, Compact, and Interpretable Tree Annotation **Authors:** [Slav Petrov](https://md.research.elamur.ai/free/en/authors/slav-petrov/), Leon Barrett, Romain Thibaux and [Dan Klein](https://md.research.elamur.ai/free/en/authors/dan-klein/) · **Year:** 2006 · **Venue:** Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL (COLING-ACL 2006) **Link:** [aclanthology.org/P06-1055](https://aclanthology.org/P06-1055/) · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) — summary only [**789** citations](https://openalex.org/works?filter=cites:W2139621418) OpenAlex, 2026-10-14 · [**453** citations in our library](https://md.research.elamur.ai/free/en/papers/petrov-2006-learning-accurate-compact-interpretable-tree/cited-by/) of the 140,884 papers whose bibliographies we read · [Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics](https://aclanthology.org/volumes/P06-1/) · [licence](https://creativecommons.org/licenses/by-nc-sa/3.0/) - [Publisher's page](https://aclanthology.org/P06-1055/) - [PDF](https://aclanthology.org/P06-1055.pdf) - [DOI 10.3115/1220175.1220230](https://doi.org/10.3115/1220175.1220230) - [OpenAlex](https://openalex.org/W2139621418) **Authors (4)** 1. [Slav Petrov](https://openalex.org/A5062886906) [ORCID](https://orcid.org/0000-0002-5505-4861) · [Semantic Scholar](https://www.semanticscholar.org/author/1754497) · h 39 · 15,014 citations · 106 works 2. [Leon Barrett](https://openalex.org/A5001779544) [ORCID](https://orcid.org/0000-0001-9896-3259) · [Semantic Scholar](https://www.semanticscholar.org/author/37157794) · h 6 · 1,368 citations · 18 works 3. [Romain Thibaux](https://openalex.org/A5015975477) [Semantic Scholar](https://www.semanticscholar.org/author/3323298) · h 6 · 1,718 citations · 12 works 4. [Dan Klein](https://openalex.org/A5004921249) [ORCID](https://orcid.org/0000-0002-8881-1902) · [Semantic Scholar](https://www.semanticscholar.org/author/38666915) · h 74 · 25,166 citations · 293 works Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart. ## What it is about Hand-made tree annotations, which split a category such as NP into subject and object NPs, raise parser accuracy, but they are made by people for one language. The authors learn such splits automatically: every nonterminal is split into subsymbols by repeated split and merge cycles that maximize the likelihood of the training treebank, and each symbol can be split to a different degree. The learned grammar recovers the kinds of distinctions that linguists wrote by hand, and it is more compact and more accurate than earlier automatic splits with a fixed number of subsymbols. The parser reaches an F1 of 90.2% on the Penn Treebank, which is a 27% reduction in error over the base grammar. ## Ideas - I2. Merge pass for compactness: after each split cycle, merge back the subtags that do not raise dev accuracy, and report model size in weights and dev UPOS against the current perceptron. ## For Mova - I1. Latent subtags for the tagger in `en/src/ptag.rs`: split each tag into subtags by split and merge over the EWT training set, and measure UPOS accuracy on EWT dev, with the 94.74 test figure kept for the single release check. - I3. Interpretable splits: for each learned subtag, list its most frequent words and check on 100 sampled tokens whether it corresponds to a subject, object or modifier distinction; `en explain` can show the subtag chosen for each token. The tagger is `en/src/ptag.rs` with the TnT prior in `en/src/tag.rs`, the tag set is in `en/src/ud.rs`, and the explanation output is `en/src/explain.rs`. The chapter that the ideas touch is [languages/en/10-word-classes.md](https://mova.elamur.ai/free/en/docs/languages/en/10-word-classes/). Measure first: UPOS on EWT dev with split subtags against the current tagger, run twice to confirm the result is not noise. ## Institutions [🎓**University of California, Berkeley** Berkeley · United States 107 works · 205,102 citations](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) ## Cite Cite as Slav Petrov, Leon Barrett, Romain Thibaux and Dan Klein. 2006. Learning Accurate, Compact, and Interpretable Tree Annotation. Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics. The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.3115/1220175.1220230](https://doi.org/10.3115/1220175.1220230) ```bibtex @inproceedings{petrov2006learning, title = {{Learning Accurate, Compact, and Interpretable Tree Annotation}}, author = {Slav Petrov, Leon Barrett, Romain Thibaux and Dan Klein}, booktitle = {Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics}, year = {2006}, doi = {10.3115/1220175.1220230}, url = {https://doi.org/10.3115/1220175.1220230} } ``` - [← previous NLTK: The Natural Language Toolkit](https://md.research.elamur.ai/free/en/papers/bird-2006-nltk-natural-language-toolkit/) - [next → Using Encyclopedic Knowledge for Named entity Disambiguation](https://md.research.elamur.ai/free/en/papers/bunescu-2006-encyclopedic-knowledge-named-entity-disambiguation/) - [↑ back to papers of 2006](https://md.research.elamur.ai/free/en/papers/2006/) ## References 19 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. G. Ball and D. Hall. 1967. A clustering technique for summarizing multivariate data. Behavioral Science. [find](https://scholar.google.com/scholar?q=G%2E+Ball+and+D%2E+Hall%2E+1967%2E+A+clustering+technique+for+summarizing+multivariate+data%2E+Behavioral+Science%2E) 2. S. Caraballo and E. Charniak. 1998. New figures of merit for best–first probabilistic chart parsing. In Computational Lingusitics, p. 275–298. [find](https://scholar.google.com/scholar?q=S%2E+Caraballo+and+E%2E+Charniak%2E+1998%2E+New+figures+of+merit+for+best%E2%80%93first+probabilistic+chart+parsing%2E+In+Computational+Lingusitics%2C+p%2E+275%E2%80%93298%2E) 3. E. Charniak and M. Johnson. 2005. Coarse-to-fine n-best parsing and maxent discriminative reranking. In ACL’05, p. 173–180. [our card](https://md.research.elamur.ai/free/en/papers/charniak-2005-coarse-fine-n-best-parsing/) 4. E. Charniak. 1996. Tree-bank grammars. In AAAI ’96, p. 1031–1036. [find](https://scholar.google.com/scholar?q=E%2E+Charniak%2E+1996%2E+Tree%2Dbank+grammars%2E+In+AAAI+%E2%80%9996%2C+p%2E+1031%E2%80%931036%2E) 5. E. Charniak. 2000. A maximum–entropy–inspired parser. In NAACL ’00, p. 132–139. [our card](https://md.research.elamur.ai/free/en/papers/charniak-2000-maximum-entropy-inspired-parser/) 6. D. Chiang and D. Bikel. 2002. Recovering latent information in treebanks. In Computational Linguistics. [find](https://scholar.google.com/scholar?q=D%2E+Chiang+and+D%2E+Bikel%2E+2002%2E+Recovering+latent+information+in+treebanks%2E+In+Computational+Linguistics%2E) 7. N. Chomsky. 1965. Aspects of the Theory of Syntax. MIT Press. [find](https://scholar.google.com/scholar?q=N%2E+Chomsky%2E+1965%2E+Aspects+of+the+Theory+of+Syntax%2E+MIT+Press%2E) 8. M. Collins. 1999. Head-Driven Statistical Models for Natural Language Parsing. Ph.D. thesis, U. of Pennsylvania. [find](https://scholar.google.com/scholar?q=M%2E+Collins%2E+1999%2E+Head%2DDriven+Statistical+Models+for+Natural+Language+Parsing%2E+Ph%2ED%2E+thesis%2C+U%2E+of+Pennsylvania%2E) 9. J. Goodman. 1996. Parsing algorithms and metrics. In ACL ’96, p. 177–183. [find](https://scholar.google.com/scholar?q=J%2E+Goodman%2E+1996%2E+Parsing+algorithms+and+metrics%2E+In+ACL+%E2%80%9996%2C+p%2E+177%E2%80%93183%2E) 10. J. Henderson. 2004. Discriminative training of a neural network statistical parser. In ACL ’04. [find](https://scholar.google.com/scholar?q=J%2E+Henderson%2E+2004%2E+Discriminative+training+of+a+neural+network+statistical+parser%2E+In+ACL+%E2%80%9904%2E) 11. M. Johnson. 1998. PCFG models of linguistic tree representations. Computational Linguistics, 24:613–632. [our card](https://md.research.elamur.ai/free/en/papers/johnson-1998-pcfg-models-linguistic-tree-representations/) 12. D. Klein and C. Manning. 2003. Accurate unlexicalized parsing. ACL ’03, p. 423–430. [our card](https://md.research.elamur.ai/free/en/papers/klein-2003-accurate-unlexicalized-parsing/) 13. T. Matsuzaki, Y. Miyao, and J. Tsujii. 2005. Probabilistic CFG with latent annotations. In ACL ’05, p. 75–82. [our card](https://md.research.elamur.ai/free/en/papers/matsuzaki-2005-probabilistic-cfg-latent-annotations/) 14. F. Pereira and Y. Schabes. 1992. Inside-outside reestimation from partially bracketed corpora. In ACL ’92, p. 128–135. [our card](https://md.research.elamur.ai/free/en/papers/pereira-1992-inside-outside-reestimation-partially-bracketed/) 15. D. Prescher. 2005. Inducing head-driven PCFGs with latent heads: Refining a tree-bank grammar for parsing. In ECML’05. [find](https://scholar.google.com/scholar?q=D%2E+Prescher%2E+2005%2E+Inducing+head%2Ddriven+PCFGs+with+latent+heads%3A+Refining+a+tree%2Dbank+grammar+for+parsing%2E+In+ECML%E2%80%9905%2E) 16. H. Schuetze. 1998. Automatic word sense discrimination. Computational Linguistics, 24(1):97–124. [find](https://scholar.google.com/scholar?q=H%2E+Schuetze%2E+1998%2E+Automatic+word+sense+discrimination%2E+Computational+Linguistics%2C+24%281%29%3A97%E2%80%93124%2E) 17. S. Sekine and M. J. Collins. 1997. EVALB bracket scoring program. [http://nlp.cs.nyu.edu/evalb/](http://nlp.cs.nyu.edu/evalb/). [↗](http://nlp.cs.nyu.edu/evalb/) 18. K. Sima’an. 1992. Computatoinal complexity of probabilistic disambiguation. Grammars, 5:125–151. [find](https://scholar.google.com/scholar?q=K%2E+Sima%E2%80%99an%2E+1992%2E+Computatoinal+complexity+of+probabilistic+disambiguation%2E+Grammars%2C+5%3A125%E2%80%93151%2E) 19. A. Stolcke and S. Omohundro. 1994. Inducing probabilistic grammars by bayesian model merging. In Grammatical Inference and Applications, p. 106–118. [find](https://scholar.google.com/scholar?q=A%2E+Stolcke+and+S%2E+Omohundro%2E+1994%2E+Inducing+probabilistic+grammars+by+bayesian+model+merging%2E+In+Grammatical+Inference+and+Applications%2C+p%2E+106%E2%80%93118%2E)