---
title: "A Global Joint Model for Semantic Role Labeling — Toutanova 2008"
description: "Toutanova, Haghighi and Manning build a discriminative log-linear joint model over whole argument frames. 27 references, cited by 72 papers here."
authors: ["Kristina Toutanova", "Aria Haghighi", "Christopher D. Manning"]
year: 2008
venue: "Computational Linguistics"
source: "https://aclanthology.org/J08-2002/"
doi: "10.1162/coli.2008.34.2.161"
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/toutanova-2008-global-joint-model-semantic-role/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/toutanova-2008-global-joint-model-semantic-role/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2008](https://md.research.elamur.ai/free/en/papers/2008/) / A Global Joint Model for Semantic Role Labeling

# A Global Joint Model for Semantic Role Labeling

**Authors:** [Kristina Toutanova](https://md.research.elamur.ai/free/en/authors/kristina-toutanova/), [Aria Haghighi](https://md.research.elamur.ai/free/en/authors/aria-haghighi/) and [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/) · **Year:** 2008 · **Venue:** Computational Linguistics · **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/J08-2002/) · [PDF](https://aclanthology.org/J08-2002.pdf) · [DOI 10.1162/coli.2008.34.2.161](https://doi.org/10.1162/coli.2008.34.2.161) · [OpenAlex](https://openalex.org/W2172176372)

**Citations:** 142 citations (OpenAlex, 2026-10-14) · [72](https://md.research.elamur.ai/free/en/papers/toutanova-2008-global-joint-model-semantic-role/cited-by/) in our library, of the 140,884 papers whose bibliographies we read

## Summary
Most semantic role labeling (SRL) systems label each parse-tree constituent separately. This ignores a basic linguistic fact: a verb's arguments form a frame whose members constrain one another. For example, an agent rarely appears twice, and one argument's role can depend on how the others are realized. Toutanova, Haghighi and Manning build a discriminative log-linear joint model over whole argument frames. Formally it is a densely connected CRF with no Markov restrictions. Exact search over all labelings is infeasible, so a local SRL classifier first proposes n-best complete labelings, which the joint model then re-ranks. To limit overfitting, the authors use only a small set of linguistically motivated joint features. These include features of the full label sequence and features that link one argument's label to the syntactic properties of other arguments. On Propbank, the joint model clearly beats a strong local baseline, with gold and automatic parses alike. On CoNLL 2005 data, it surpasses the shared task's winning system. The work shows that statistical modeling of argument interdependencies pays off. It also shows that considering several parser outputs helps counter parsing noise.

## Key points
- On Propbank with gold-standard parse trees, the joint model lowers the local model's error rate by 24.1% when every argument is counted, and by 36.8% when only core arguments (ARG0–ARG5) are counted.
- With automatic parses, the error reductions are smaller: 8.3% on all arguments and 10.3% on core arguments.
- Inference uses Collins-style re-ranking of the local model's n-best assignments. The joint constraints are learned as soft statistical preferences, unlike the hard, hand-written ILP constraints of Punyakanok et al.
- On the CoNLL 2005 data, choosing among the top five Charniak parses yields an F-Measure of 80.32 on WSJ Test (winning system: 79.44) and 68.81 on Brown Test (winning system: 67.75).
- These scores exceed the authors' original shared-task submission (78.45 on WSJ Test) because of two fixes: continuation labels are now added only to core arguments, and a bug in how forward quotes reached the Charniak parser was corrected.

*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: [🎭 Semantic role labeling](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/)

## Institutions

- [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) — University, Stanford, United States · 248 works · 214,804 citations
- [University of California, Berkeley](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) — University, Berkeley, United States · 107 works · 205,102 citations
- [Microsoft](https://md.research.elamur.ai/free/en/companies/microsoft/) — Company, Redmond, United States · 193 works · 110,465 citations

## Cite

Cite as: Kristina Toutanova, Aria Haghighi and Christopher D. Manning. 2008. A Global Joint Model for Semantic Role Labeling. Computational Linguistics.

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

```bibtex
@article{toutanova2008global,
  title = {{A Global Joint Model for Semantic Role Labeling}},
  author = {Kristina Toutanova, Aria Haghighi and Christopher D. Manning},
  journal = {Computational Linguistics},
  year = {2008},
  doi = {10.1162/coli.2008.34.2.161},
  url = {https://doi.org/10.1162/coli.2008.34.2.161}
}
```

- [← previous Arabic Morphological Tagging, Diacritization, and Lemmatization Using Lexeme Models and Feature Ranking](https://md.research.elamur.ai/free/en/papers/roth-2008-arabic-morphological-tagging-diacritization-lemmatization/)
- [next → Easily Identifiable Discourse Relations](https://md.research.elamur.ai/free/en/papers/pitler-2008-easily-identifiable-discourse-relations/)
- [↑ back to papers of 2008](https://md.research.elamur.ai/free/en/papers/2008/)

## References

27 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Baker, Collin, Charles Fillmore, and John Lowe. 1998. The Berkeley Framenet project. In Proceedings of COLING-ACL, pages 86–90, San Francisco, CA. [our card](https://md.research.elamur.ai/free/en/papers/baker-1998-berkeley-framenet/)
2. Carreras, Xavier and Luı́s Màrquez. 2004. Introduction to the CoNLL-2004 shared task: Semantic role labeling. In Proceedings of CoNLL, pages 89–97, Boston, MA. [find](https://scholar.google.com/scholar?q=Carreras%2C+Xavier+and+Lu%C4%B1%CC%81s+Ma%CC%80rquez%2E+2004%2E+Introduction+to+the+CoNLL%2D2004+shared+task%3A+Semantic+role+labeling%2E+In+Proceedings+of+CoNLL%2C+pages+89%E2%80%9397%2C+Boston%2C+MA%2E)
3. Carreras, Xavier and Luı́s Màrquez. 2005. Introduction to the CoNLL-2005 shared task: Semantic role labeling. In Proceedings of CoNLL, pages 152–164, Ann Arbor, MI. [our card](https://md.research.elamur.ai/free/en/papers/carreras-2005-introduction-conll-2005-shared-task/)
4. Charniak, Eugene. 2000. A maximum-entropy-inspired parser. In Proceedings of NAACL, pages 132–139, Seattle, WA. [our card](https://md.research.elamur.ai/free/en/papers/charniak-2000-maximum-entropy-inspired-parser/)
5. Charniak, Eugene and Mark Johnson. 2005. Coarse-to-fine n-best parsing and MaxEnt discriminative reranking. In Proceedings of ACL, pages 173–180, Ann Arbor, MI. [our card](https://md.research.elamur.ai/free/en/papers/charniak-2005-coarse-fine-n-best-parsing/)
6. Cohn, Trevor and Philip Blunsom. 2005. Semantic role labelling with tree conditional random fields. In Proceedings of CoNLL, pages 169–172, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Cohn%2C+Trevor+and+Philip+Blunsom%2E+2005%2E+Semantic+role+labelling+with+tree+conditional+random+fields%2E+In+Proceedings+of+CoNLL%2C+pages+169%E2%80%93172%2C+Ann+Arbor%2C+MI%2E)
7. Collins, Michael. 2000. Discriminative reranking for natural language parsing. In Proceedings of ICML, pages 175–182, Stanford, CA. [our card](https://md.research.elamur.ai/free/en/papers/collins-2000-discriminative-reranking-natural-language-parsing/)
8. Finkel, Jenny, Christopher Manning, and Andrew Ng. 2006. Solving the problem of cascading errors: Approximate bayesian inference for linguistic annotation pipelines. In Proceedings of EMNLP, pages 618–626, Sydney, Australia. [find](https://scholar.google.com/scholar?q=Finkel%2C+Jenny%2C+Christopher+Manning%2C+and+Andrew+Ng%2E+2006%2E+Solving+the+problem+of+cascading+errors%3A+Approximate+bayesian+inference+for+linguistic+annotation+pipelines%2E+In+Proceedings+of+EMNLP%2C+pages+618)
9. Gildea, Daniel and Daniel Jurafsky. 2002. Automatic labeling of semantic roles. Computational Linguistics, 28(3):245–288. [our card](https://md.research.elamur.ai/free/en/papers/gildea-2002-automatic-labeling-semantic-roles/)
10. Hacioglu, Kadri. 2004. A lightweight semantic chunking model based on tagging. In Proceedings of HLT-NAACL: Short Papers, pages 145–148, Boston, MA. [find](https://scholar.google.com/scholar?q=Hacioglu%2C+Kadri%2E+2004%2E+A+lightweight+semantic+chunking+model+based+on+tagging%2E+In+Proceedings+of+HLT%2DNAACL%3A+Short+Papers%2C+pages+145%E2%80%93148%2C+Boston%2C+MA%2E)
11. Haghighi, Aria, Kristina Toutanova, and Christopher D. Manning. 2005. A joint model for semantic role labeling. In Proceedings of CoNLL, pages 173–176, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Haghighi%2C+Aria%2C+Kristina+Toutanova%2C+and+Christopher+D%2E+Manning%2E+2005%2E+A+joint+model+for+semantic+role+labeling%2E+In+Proceedings+of+CoNLL%2C+pages+173%E2%80%93176%2C+Ann+Arbor%2C+MI%2E)
12. Lafferty, John, Andrew McCallum, and Fernando Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of ICML, pages 282–289, Williamstown, MA. [find](https://scholar.google.com/scholar?q=Lafferty%2C+John%2C+Andrew+McCallum%2C+and+Fernando+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+Williamst)
13. Levy, Roger and Chris Manning. 2004. Deep dependencies from context-free statistical parsers: correcting the surface dependency approximation. In Proceedings of ACL, pages 327–334, Barcelona, Spain. [find](https://scholar.google.com/scholar?q=Levy%2C+Roger+and+Chris+Manning%2E+2004%2E+Deep+dependencies+from+context%2Dfree+statistical+parsers%3A+correcting+the+surface+dependency+approximation%2E+In+Proceedings+of+ACL%2C+pages+327%E2%80%93334%2C+Barcelona%2C+Spain%2E)
14. Màrquez, Luı́s, Mihai Surdeanu, Pere Comas, and Jordi Turmo. 2005. A robust combination strategy for semantic role labeling. In Proceedings of EMNLP, pages 644–651, Vancouver, Canada. [find](https://scholar.google.com/scholar?q=Ma%CC%80rquez%2C+Lu%C4%B1%CC%81s%2C+Mihai+Surdeanu%2C+Pere+Comas%2C+and+Jordi+Turmo%2E+2005%2E+A+robust+combination+strategy+for+semantic+role+labeling%2E+In+Proceedings+of+EMNLP%2C+pages+644%E2%80%93651%2C+Vancouver%2C+Canada%2E)
15. McCallum, Andrew, Dayne Freitag, and Fernando Pereira. 2000. Maximum entropy Markov models for information extraction and segmentation. In Proceedings of ICML, pages 591–598, Stanford, CA. [find](https://scholar.google.com/scholar?q=McCallum%2C+Andrew%2C+Dayne+Freitag%2C+and+Fernando+Pereira%2E+2000%2E+Maximum+entropy+Markov+models+for+information+extraction+and+segmentation%2E+In+Proceedings+of+ICML%2C+pages+591%E2%80%93598%2C+Stanford%2C+CA%2E)
16. Palmer, Martha, Dan Gildea, and Paul Kingsbury. 2005. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–105. [our card](https://md.research.elamur.ai/free/en/papers/palmer-2005-proposition-bank-annotated-corpus-semantic/)
17. Pradhan, Sameer, Kadri Hacioglu, Valerie Krugler, Wayne Ward, James Martin, and Dan Jurafsky. 2005. Support vector learning for semantic argument classification. Machine Learning Journal, 60(1):11–39. [find](https://scholar.google.com/scholar?q=Pradhan%2C+Sameer%2C+Kadri+Hacioglu%2C+Valerie+Krugler%2C+Wayne+Ward%2C+James+Martin%2C+and+Dan+Jurafsky%2E+2005%2E+Support+vector+learning+for+semantic+argument+classification%2E+Machine+Learning+Journal%2C+60%281%29%3A11%E2%80%9339%2E)
18. Pradhan, Sameer, Wayne Ward, Kadri Hacioglu, James Martin, and Dan Jurafsky. 2004. Shallow semantic parsing using support vector machines. In Proceedings of HLT-NAACL, pages 233–240, Boston, MA. [our card](https://md.research.elamur.ai/free/en/papers/pradhan-2004-shallow-semantic-parsing-support-vector/)
19. Pradhan, Sameer, Wayne Ward, Kadri Hacioglu, James Martin, and Daniel Jurafsky. 2005. Semantic role labeling using different syntactic views. In Proceedings of ACL, pages 581–588, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Pradhan%2C+Sameer%2C+Wayne+Ward%2C+Kadri+Hacioglu%2C+James+Martin%2C+and+Daniel+Jurafsky%2E+2005%2E+Semantic+role+labeling+using+different+syntactic+views%2E+In+Proceedings+of+ACL%2C+pages+581%E2%80%93588%2C+Ann+Arbor%2C+MI%2E)
20. Punyakanok, Vasin and Dan Roth. 2001. The use of classifiers in sequential inference. In Proceedings of NIPS, pages 995–1001, Vancouver, Canada. [find](https://scholar.google.com/scholar?q=Punyakanok%2C+Vasin+and+Dan+Roth%2E+2001%2E+The+use+of+classifiers+in+sequential+inference%2E+In+Proceedings+of+NIPS%2C+pages+995%E2%80%931001%2C+Vancouver%2C+Canada%2E)
21. Punyakanok, Vasin, Dan Roth, and Wen-tau Yih. 2005. The necessity of syntactic parsing for semantic role labeling. In Proceedings of IJCAI, pages 1117–1123, Acapulco, Mexico. [find](https://scholar.google.com/scholar?q=Punyakanok%2C+Vasin%2C+Dan+Roth%2C+and+Wen%2Dtau+Yih%2E+2005%2E+The+necessity+of+syntactic+parsing+for+semantic+role+labeling%2E+In+Proceedings+of+IJCAI%2C+pages+1117%E2%80%931123%2C+Acapulco%2C+Mexico%2E)
22. Punyakanok, Vasin, Dan Roth, Wen-tau Yih, Dav Zimak, and Yuancheng Tu. 2004. Semantic role labeling via generalized inference over classifiers. In Proceedings of CoNLL, pages 130–133, Boston, MA. [find](https://scholar.google.com/scholar?q=Punyakanok%2C+Vasin%2C+Dan+Roth%2C+Wen%2Dtau+Yih%2C+Dav+Zimak%2C+and+Yuancheng+Tu%2E+2004%2E+Semantic+role+labeling+via+generalized+inference+over+classifiers%2E+In+Proceedings+of+CoNLL%2C+pages+130%E2%80%93133%2C+Boston%2C+MA%2E)
23. Roland, Douglas and Daniel Jurafsky. 2002. Verb sense and verb subcategorization probabilities. In Paola Merlo and Suzanne Stevenson, editors, The Lexical Basis of Sentence Processing: Formal, Computational, and Experimental Issues. John Benjamins, Amsterdam, pages 325–345. [find](https://scholar.google.com/scholar?q=Roland%2C+Douglas+and+Daniel+Jurafsky%2E+2002%2E+Verb+sense+and+verb+subcategorization+probabilities%2E+In+Paola+Merlo+and+Suzanne+Stevenson%2C+editors%2C+The+Lexical+Basis+of+Sentence+Processing%3A+Formal%2C+Computa)
24. Sha, Fei and Fernando Pereira. 2003. Shallow parsing with conditional random fields. In Proceedings of HLT-NAACL, pages 134–141, Edmonton, Canada. [find](https://scholar.google.com/scholar?q=Sha%2C+Fei+and+Fernando+Pereira%2E+2003%2E+Shallow+parsing+with+conditional+random+fields%2E+In+Proceedings+of+HLT%2DNAACL%2C+pages+134%E2%80%93141%2C+Edmonton%2C+Canada%2E)
25. Surdeanu, Mihai, Sanda Harabagiu, John Williams, and Paul Aarseth. 2003. Using predicate-argument structures for information extraction. In Proceedings of ACL, pages 8–15, Sapporo, Japan. [our card](https://md.research.elamur.ai/free/en/papers/surdeanu-2003-predicate-argument-structures-information-extraction/)
26. Xue, Nianwen and Martha Palmer. 2004. Calibrating features for semantic role labeling. In Proceedings of EMNLP, pages 88–94, Barcelona, Spain. [find](https://scholar.google.com/scholar?q=Xue%2C+Nianwen+and+Martha+Palmer%2E+2004%2E+Calibrating+features+for+semantic+role+labeling%2E+In+Proceedings+of+EMNLP%2C+pages+88%E2%80%9394%2C+Barcelona%2C+Spain%2E)
27. Yi, Szu-ting and Martha Palmer. 2005. The integration of syntactic parsing and semantic role labeling. In Proceedings of CoNLL, pages 237–240, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Yi%2C+Szu%2Dting+and+Martha+Palmer%2E+2005%2E+The+integration+of+syntactic+parsing+and+semantic+role+labeling%2E+In+Proceedings+of+CoNLL%2C+pages+237%E2%80%93240%2C+Ann+Arbor%2C+MI%2E)