---
title: "Efficient Inference and Structured Learning for Semantic Role"
description: "The authors build a two-step pipeline: frame identification, followed by role labeling over… 70.3 F1. 34 references, cited by 48 papers here."
authors: ["Oscar Täckström", "Kuzman Ganchev", "Dipanjan Das"]
year: 2015
venue: "Transactions of the Association for Computational Linguistics"
source: "https://aclanthology.org/Q15-1003/"
doi: "10.1162/tacl_a_00120"
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/tackstrom-2015-efficient-inference-structured-learning-semantic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tackstrom-2015-efficient-inference-structured-learning-semantic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2015](https://md.research.elamur.ai/free/en/papers/2015/page/2/) / Efficient Inference and Structured Learning for Semantic Role Labeling

# Efficient Inference and Structured Learning for Semantic Role Labeling

**Authors:** [Oscar Täckström](https://md.research.elamur.ai/free/en/authors/oscar-tackstrom/), [Kuzman Ganchev](https://md.research.elamur.ai/free/en/authors/kuzman-ganchev/) and [Dipanjan Das](https://md.research.elamur.ai/free/en/authors/dipanjan-das/) · **Year:** 2015 · **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) 2015](https://md.research.elamur.ai/free/en/venues/tacl/2015/)) · **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/Q15-1003/) · [PDF](https://aclanthology.org/Q15-1003.pdf) · [DOI 10.1162/tacl\_a\_00120](https://doi.org/10.1162/tacl_a_00120) · [OpenAlex](https://openalex.org/W2114590102)

**Citations:** 79 citations (OpenAlex, 2026-10-14) · [48](https://md.research.elamur.ai/free/en/papers/tackstrom-2015-efficient-inference-structured-learning-semantic/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper tackles constrained inference for semantic role labeling (SRL). Earlier systems imposed linguistic constraints, such as banning overlapping arguments or repeated core roles, either through approximations or through generic integer linear programming (ILP) solvers. The authors build a two-step pipeline: frame identification, followed by role labeling over candidate spans taken from a dependency parse. They replace the ILP with a dynamic program that exactly enforces most of the constraints from Punyakanok et al. (2008) and falls back to k-best search for the rest. Because the dynamic program can also compute marginals, the authors can train a globally-normalized log-linear model with the constraints active during learning, rather than only at decoding time. The method returns the same answers as an ILP solver at a fraction of the runtime. The structured model outperforms its locally trained counterpart on CoNLL 2005, OntoNotes 5.0 and FrameNet 1.5. This shows that exact, fast, probabilistic SRL inference is practical without ensembles or reranking.

## Key points
- **Speed:** On the OntoNotes 5.0 dev set, relative to unconstrained local inference, the timings were:
  - DP with k-best: about 6.2×
  - Gurobi: 25×
  - SCIP: about 199×

  The DP is therefore over four times faster than Gurobi, with no constraint violations. When k-best search was needed, k averaged 1.8, with a maximum of 80.
- **OntoNotes 5.0:** Compared with Pradhan et al. (2013), the model cuts F1 error by about 15% and complete-analysis error by about 20%. Frame identification reaches 94.9% test accuracy versus 92.8%. Comparability is limited by errors in the original data release.
- **FrameNet 1.5:** Frame identification uses the WSABIE model. Structured/DP reaches 70.3 F1, compared with 69.9 for Hermann et al. (2014), and 33.8 complete-analysis score.
- **CoNLL 2005:** The system uses a single model and one dependency parse. It beats other single-model systems on the WSJ and Brown test sets and is competitive with ensemble methods.

*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

- [Google](https://md.research.elamur.ai/free/en/companies/google/) — Company, Mountain View, United States · 353 works · 364,806 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 (2): [🎭 Semantic role labeling](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/) · 132 works · [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 77 works

## Cite

Cite as: Oscar Täckström, Kuzman Ganchev and Dipanjan Das. 2015. Efficient Inference and Structured Learning for Semantic Role Labeling. Transactions of the Association for Computational Linguistics.

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

```bibtex
@article{tackstrom2015efficient,
  title = {{Efficient Inference and Structured Learning for Semantic Role Labeling}},
  author = {Oscar Täckström, Kuzman Ganchev and Dipanjan Das},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2015},
  doi = {10.1162/tacl\_a\_00120},
  url = {https://doi.org/10.1162/tacl_a_00120}
}
```

- [← previous Machine Translation Experiments on PADIC: A Parallel Arabic DIalect Corpus](https://md.research.elamur.ai/free/en/papers/meftouh-2015-machine-translation-experiments-padic-parallel/)
- [next → Sparse, Contextually Informed Models for Irony Detection: Exploiting User Communities, Entities and Sentiment](https://md.research.elamur.ai/free/en/papers/wallace-2015-sparse-contextually-informed-models-irony/)
- [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/page/2/)

## References

34 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. [The Berkeley FrameNet project](https://md.research.elamur.ai/free/en/papers/baker-1998-berkeley-framenet/). In Proceedings of ACL.
2. Collin Baker, Michael Ellsworth, and Katrin Erk. 2007. [Semeval-2007 task 19: Frame semantic structure extraction](https://md.research.elamur.ai/free/en/papers/baker-2007-semeval-2007-task-19-frame/). In Proceedings of SemEval. 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. Computati…
3. Xavier Carreras and Lluís Màrquez. 2004. Introduction to the CoNLL-2004 shared task: Semantic role labeling. In Proceedings of CoNLL. [find](https://scholar.google.com/scholar?q=Xavier+Carreras+and+Llu%C3%ADs+M%C3%A0rquez%2E+2004%2E+Introduction+to+the+CoNLL%2D2004+shared+task%3A+Semantic+role+labeling%2E+In+Proceedings+of+CoNLL%2E)
4. Xavier Carreras and Lluís Màrquez. 2005. [Introduction to the CoNLL-2005 shared task: Semantic role labeling](https://md.research.elamur.ai/free/en/papers/carreras-2005-introduction-conll-2005-shared-task/). In Proceedings of CoNLL.
5. Dipanjan Das, André F. T. Martins, and Noah A. Smith. 2012. An exact dual decomposition algorithm for shallow semantic parsing with constraints. In Proceedings of *SEM. [find](https://scholar.google.com/scholar?q=Dipanjan+Das%2C+Andr%C3%A9+F%2E+T%2E+Martins%2C+and+Noah+A%2E+Smith%2E+2012%2E+An+exact+dual+decomposition+algorithm+for+shallow+semantic+parsing+with+constraints%2E+In+Proceedings+of+%2ASEM%2E)
6. Dipanjan Das, Desai Chen, André F. T. Martins, Nathan Schneider, and Noah A. Smith. 2014. [Frame-semantic parsing](https://md.research.elamur.ai/free/en/papers/das-2014-frame-semantic-parsing/). Computational Linguistics, 40(1):9–56.
7. Marie-Catherine de Marneffe and Christopher D. Manning, 2013. Stanford typed dependencies manual. [find](https://scholar.google.com/scholar?q=Marie%2DCatherine+de+Marneffe+and+Christopher+D%2E+Manning%2C+2013%2E+Stanford+typed+dependencies+manual%2E)
8. Bradley Efron and Robert J Tibshirani. 1994. An introduction to the bootstrap. CRC press. [find](https://scholar.google.com/scholar?q=Bradley+Efron+and+Robert+J+Tibshirani%2E+1994%2E+An+introduction+to+the+bootstrap%2E+CRC+press%2E)
9. Matthew Gerber and Joyce Y. Chai. 2010. Beyond Nom-Bank: A study of implicit arguments for nominal predicates. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Matthew+Gerber+and+Joyce+Y%2E+Chai%2E+2010%2E+Beyond+Nom%2DBank%3A+A+study+of+implicit+arguments+for+nominal+predicates%2E+In+Proceedings+of+ACL%2E)
10. Daniel Gildea and Daniel Jurafsky. 2002. [Automatic labeling of semantic roles](https://md.research.elamur.ai/free/en/papers/gildea-2002-automatic-labeling-semantic-roles/). Computational Linguistics, 28(3):245–288. Jan Hajič, Massimiliano Ciaramita, Richard Johansson, Daisuke Kawahara, Maria Antònia Martí, Lluís Màrquez, Adam Meyers, Joakim Nivre, Sebastian Padó, Jan Štěpánek, Pavel Straň…
11. Karl Moritz Hermann, Dipanjan Das, Jason Weston, and Kuzman Ganchev. 2014. [Semantic frame identification with distributed word representations](https://md.research.elamur.ai/free/en/papers/hermann-2014-semantic-frame-identification-distributed-word/). In Proceedings of ACL.
12. Liang Huang and David Chiang. 2005. Better k-best parsing. In Proceedings of IWPT. [find](https://scholar.google.com/scholar?q=Liang+Huang+and+David+Chiang%2E+2005%2E+Better+k%2Dbest+parsing%2E+In+Proceedings+of+IWPT%2E)
13. Richard Johansson and Pierre Nugues. 2008. [Dependency-based semantic role labeling of PropBank](https://md.research.elamur.ai/free/en/papers/johansson-2008-dependency-based-semantic-role-labeling/). In Proceedings of EMNLP.
14. John Lafferty, Andrew McCallum, and Fernando Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of ICML. [find](https://scholar.google.com/scholar?q=John+Lafferty%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%2E)
15. Mitchell P. Marcus, Mary Ann Marcinkiewicz, and Beatrice Santorini. 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.
16. Lluís Màrquez, Xavier Carreras, Kenneth C. Litkowski, and Suzanne Stevenson. 2008. Semantic role labeling: An introduction to the special issue. Computational Linguistics, 34(2):145–159. [find](https://scholar.google.com/scholar?q=Llu%C3%ADs+M%C3%A0rquez%2C+Xavier+Carreras%2C+Kenneth+C%2E+Litkowski%2C+and+Suzanne+Stevenson%2E+2008%2E+Semantic+role+labeling%3A+An+introduction+to+the+special+issue%2E+Computational+Linguistics%2C+34%282%29%3A145%E2%80%93159%2E)
17. André F. T. Martins, Noah A. Smith, Pedro M. Q. Aguiar, and Mário A. T. Figueiredo. 2011. Dual decomposition with many overlapping components. In Proceedings of EMNLP. [find](https://scholar.google.com/scholar?q=Andr%C3%A9+F%2E+T%2E+Martins%2C+Noah+A%2E+Smith%2C+Pedro+M%2E+Q%2E+Aguiar%2C+and+M%C3%A1rio+A%2E+T%2E+Figueiredo%2E+2011%2E+Dual+decomposition+with+many+overlapping+components%2E+In+Proceedings+of+EMNLP%2E)
18. Adam Meyers, Ruth Reeves, Catherine Macleod, Rachel Szekely, Veronika Zielinska, Brian Young, and Ralph Grishman. 2004. [The NomBank project: An interim report](https://md.research.elamur.ai/free/en/papers/meyers-2004-nombank-project-interim-report/). In Proceedings of NAACL/HLT Workshop on Frontiers in Corpus Annotation.
19. Ivan Meza-Ruiz and Sebastian Riedel. 2009. Jointly identifying predicates, arguments and senses using Markov Logic. In Proceedings of NAACL-HLT. [find](https://scholar.google.com/scholar?q=Ivan+Meza%2DRuiz+and+Sebastian+Riedel%2E+2009%2E+Jointly+identifying+predicates%2C+arguments+and+senses+using+Markov+Logic%2E+In+Proceedings+of+NAACL%2DHLT%2E)
20. Martha Palmer, Daniel Gildea, and Paul Kingsbury. 2005. [The Proposition bank: An annotated corpus of semantic roles](https://md.research.elamur.ai/free/en/papers/palmer-2005-proposition-bank-annotated-corpus-semantic/). Computational Linguistics, 31(1):71–106.
21. Sameer Pradhan, Kadri Hacioglu, Valerie Krugler, Wayne Ward, James H. Martin, and Daniel Jurafsky. 2005. Support vector learning for semantic argument classification. Machine Learning, 60(1-3):11–39. [find](https://scholar.google.com/scholar?q=Sameer+Pradhan%2C+Kadri+Hacioglu%2C+Valerie+Krugler%2C+Wayne+Ward%2C+James+H%2E+Martin%2C+and+Daniel+Jurafsky%2E+2005%2E+Support+vector+learning+for+semantic+argument+classification%2E+Machine+Learning%2C+60%281%2D3%29%3A11%E2%80%9339%2E)
22. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Tou Hwee Ng, Anders Björkelund, Olga Uryupina, Yuchen Zhang, and Zhi Zhong. 2013. Towards robust linguistic analysis using OntoNotes. In Proceedings of CoNLL. [find](https://scholar.google.com/scholar?q=Sameer+Pradhan%2C+Alessandro+Moschitti%2C+Nianwen+Xue%2C+Tou+Hwee+Ng%2C+Anders+Bj%C3%B6rkelund%2C+Olga+Uryupina%2C+Yuchen+Zhang%2C+and+Zhi+Zhong%2E+2013%2E+Towards+robust+linguistic+analysis+using+OntoNotes%2E+In+Proceedings+)
23. Vasin Punyakanok, Dan Roth, and Wen-tau Yih. 2008. [The importance of syntactic parsing and inference in semantic role labeling](https://md.research.elamur.ai/free/en/papers/punyakanok-2008-importance-syntactic-parsing-inference-semantic/). Computational Linguistics, 34(2):257–287.
24. Sebastian Riedel and David A. Smith. 2010. Relaxed marginal inference and its application to dependency parsing. In Proceedings of NAACL-HLT. [find](https://scholar.google.com/scholar?q=Sebastian+Riedel+and+David+A%2E+Smith%2E+2010%2E+Relaxed+marginal+inference+and+its+application+to+dependency+parsing%2E+In+Proceedings+of+NAACL%2DHLT%2E)
25. Mihai Surdeanu, Lluís Màrquez, Xavier Carreras, and Pere R. Comas. 2007. Combination strategies for semantic role labeling. Journal of Artificial Intelligence Research, 29(1):105–151. [find](https://scholar.google.com/scholar?q=Mihai+Surdeanu%2C+Llu%C3%ADs+M%C3%A0rquez%2C+Xavier+Carreras%2C+and+Pere+R%2E+Comas%2E+2007%2E+Combination+strategies+for+semantic+role+labeling%2E+Journal+of+Artificial+Intelligence+Research%2C+29%281%29%3A105%E2%80%93151%2E)
26. Mihai Surdeanu, Richard Johansson, Adam Meyers, Lluís Màrquez, and Joakim Nivre. 2008. [find](https://scholar.google.com/scholar?q=Mihai+Surdeanu%2C+Richard+Johansson%2C+Adam+Meyers%2C+Llu%C3%ADs+M%C3%A0rquez%2C+and+Joakim+Nivre%2E+2008%2E)
27. [The CoNLL 2008 shared task on joint parsing of syntactic and semantic dependencies](https://md.research.elamur.ai/free/en/papers/surdeanu-2008-conll-2008-shared-task-joint/). In Proceedings of CoNLL.
28. Kristina Toutanova, Aria Haghighi, and Christopher D. Manning. 2008. [A global joint model for semantic role labeling](https://md.research.elamur.ai/free/en/papers/toutanova-2008-global-joint-model-semantic-role/). Computational Linguistics, 34(2):161–191.
29. Roy W. Tromble and Jason Eisner. 2006. A fast finite-state relaxation method for enforcing global constraints on sequence decoding. In Proceedings of NAACL-HLT. [find](https://scholar.google.com/scholar?q=Roy+W%2E+Tromble+and+Jason+Eisner%2E+2006%2E+A+fast+finite%2Dstate+relaxation+method+for+enforcing+global+constraints+on+sequence+decoding%2E+In+Proceedings+of+NAACL%2DHLT%2E)
30. Joseph Turian, Lev 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 ACL.
31. Ralph Weischedel, Eduard Hovy, Martha Palmer, Mitch Marcus, Robert Belvin, Sameer Pradhan, Lance Ramshaw, and Nianwen Xue. 2011. OntoNotes: A large training corpus for enhanced processing. In J. Olive, C. Christianson, and J. McCary, editors, Handbook of Natural Language Processing and Machine Trans… [find](https://scholar.google.com/scholar?q=Ralph+Weischedel%2C+Eduard+Hovy%2C+Martha+Palmer%2C+Mitch+Marcus%2C+Robert+Belvin%2C+Sameer+Pradhan%2C+Lance+Ramshaw%2C+and+Nianwen+Xue%2E+2011%2E+OntoNotes%3A+A+large+training+corpus+for+enhanced+processing%2E+In+J%2E+Olive)
32. Springer. Jason Weston, Samy Bengio, and Nicolas Usunier. 2011. WSABIE: Scaling up to large vocabulary image annotation. In Proceedings of IJCAI. [find](https://scholar.google.com/scholar?q=Springer%2E+Jason+Weston%2C+Samy+Bengio%2C+and+Nicolas+Usunier%2E+2011%2E+WSABIE%3A+Scaling+up+to+large+vocabulary+image+annotation%2E+In+Proceedings+of+IJCAI%2E)
33. Nianwen Xue and Martha Palmer. 2004. Calibrating features for semantic role labeling. In Proceedings of EMNLP. [find](https://scholar.google.com/scholar?q=Nianwen+Xue+and+Martha+Palmer%2E+2004%2E+Calibrating+features+for+semantic+role+labeling%2E+In+Proceedings+of+EMNLP%2E)
34. Hao Zhang and Ryan McDonald. 2014. Enforcing structural diversity in cube-pruned dependency parsing. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Hao+Zhang+and+Ryan+McDonald%2E+2014%2E+Enforcing+structural+diversity+in+cube%2Dpruned+dependency+parsing%2E+In+Proceedings+of+ACL%2E)

*Updated 24 October 2026*