---
title: "Tree Kernels for Semantic Role Labeling — Moschitti 2008"
description: "They design several mappings for different stages of an SRL pipeline: boundary detection, role… 2.5 points. 42 references, cited by 49 papers here."
authors: ["Alessandro Moschitti", "Daniele Pighin", "Roberto Basili"]
year: 2008
venue: "Computational Linguistics"
source: "https://aclanthology.org/J08-2003/"
doi: "10.1162/coli.2008.34.2.193"
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/moschitti-2008-tree-kernels-semantic-role-labeling/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/moschitti-2008-tree-kernels-semantic-role-labeling/)

[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/) / Tree Kernels for Semantic Role Labeling

# Tree Kernels for Semantic Role Labeling

**Authors:** [Alessandro Moschitti](https://md.research.elamur.ai/free/en/authors/alessandro-moschitti/), [Daniele Pighin](https://md.research.elamur.ai/free/en/authors/daniele-pighin/) and [Roberto Basili](https://md.research.elamur.ai/free/en/authors/roberto-basili/) · **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/J08-2003/) · [PDF](https://aclanthology.org/J08-2003.pdf) · [DOI 10.1162/coli.2008.34.2.193](https://doi.org/10.1162/coli.2008.34.2.193) · [OpenAlex](https://openalex.org/W1987486061)

**Citations:** 153 citations (OpenAlex, 2026-10-14) · [49](https://md.research.elamur.ai/free/en/papers/moschitti-2008-tree-kernels-semantic-role-labeling/cited-by/) in our library, of the 140,884 papers whose bibliographies we read

## Summary
Semantic role labeling (SRL) systems usually depend on many hand-crafted syntactic features, each needing its own extraction code. This article asks whether tree kernels can automate that feature engineering. The authors split a kernel into two parts. Canonical mappings turn a parse tree into a structure that reflects predicate–argument information. Feature extraction functions then expand that structure into all of its sub-fragments. They design several mappings for different stages of an SRL pipeline: boundary detection, role classification, and re-ranking of whole annotations. Each was tested with support vector machines on the CoNLL 2005 shared task data (PropBank), both alone and combined with standard attribute–value features. Tree kernels consistently helped. The gains were largest with little training data, where the kernels act as a back-off model for sparse features. In re-ranking, they let the authors build structural features that would be hard to specify by hand. The broader point is that tree kernels offer a generic, portable route to feature design for many NLP tasks, not just SRL.

## Key points
- With limited training data, the improved kernel based on the AST m1 mapping added about 5 absolute points over a state-of-the-art boundary classifier. For argument classification, the gain was smaller but consistent, around 3%.
- Marking relevant parse-tree nodes addresses a known weakness of tree kernels in boundary detection, where correct and incorrect candidates otherwise share most of their tree structure.
- Structured features in the re-ranker gave about 2.5 points over the baseline. The model's theoretical upper bound was still roughly 6 points higher.
- The re-ranker was trained on just 2 of the 22 training sections, yet matched CoNLL 2005 systems that do not use tree kernels. Adding local standard features to it reduced accuracy by about 0.5 points on Sections 12 and 24.
- Proposed future work includes:
  - pairing the ST, SST, and PT extraction functions with the new mappings, including PT on dependency trees;
  - training on the full CoNLL 2005 data;
  - moving the most useful fragments into explicit feature spaces for speed;
  - using multiple parse views of each sentence.

*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

- [Fondazione Bruno Kessler](https://md.research.elamur.ai/free/en/labs/fondazione-bruno-kessler/) — Research institute, Trento, Italy · 18 works · 42,903 citations
- [University of Trento](https://md.research.elamur.ai/free/en/universities/university-of-trento/) — University, Trento, Italy · 50 works · 13,649 citations
- [University of Rome Tor Vergata](https://md.research.elamur.ai/free/en/universities/university-of-rome-tor-vergata/) — University, Rome, Italy · 5 works · 1,207 citations

## Cite

Cite as: Alessandro Moschitti, Daniele Pighin and Roberto Basili. 2008. Tree Kernels for Semantic Role Labeling. Computational Linguistics.

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

```bibtex
@article{moschitti2008tree,
  title = {{Tree Kernels for Semantic Role Labeling}},
  author = {Alessandro Moschitti, Daniele Pighin and Roberto Basili},
  journal = {Computational Linguistics},
  year = {2008},
  doi = {10.1162/coli.2008.34.2.193},
  url = {https://doi.org/10.1162/coli.2008.34.2.193}
}
```

- [← previous A Classifier-Based Approach to Preposition and Determiner Error Correction in L2 English](https://md.research.elamur.ai/free/en/papers/felice-2008-classifier-based-approach-preposition-determiner/)
- [next → Anaphoric Annotation in the ARRAU Corpus](https://md.research.elamur.ai/free/en/papers/poesio-2008-anaphoric-annotation-arrau-corpus/)
- [↑ back to papers of 2008](https://md.research.elamur.ai/free/en/papers/2008/)

## References

42 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 F., Charles J. Fillmore, and John B. Lowe. 1998. The Berkeley FrameNet project. In COLING-ACL ’98: Proceedings of the Conference, pages 86–90, Montréal, Canada. [our card](https://md.research.elamur.ai/free/en/papers/baker-1998-berkeley-framenet/)
2. Carreras, Xavier and Lluı́s Màrquez. 2004. Introduction to the CoNLL-2004 shared task: Semantic role labeling. In HLT-NAACL 2004 Workshop: Eighth Conference on Computational Natural Language Learning (CoNLL-2004), pages 89–97, Boston, MA. [find](https://scholar.google.com/scholar?q=Carreras%2C+Xavier+and+Llu%C4%B1%CC%81s+Ma%CC%80rquez%2E+2004%2E+Introduction+to+the+CoNLL%2D2004+shared+task%3A+Semantic+role+labeling%2E+In+HLT%2DNAACL+2004+Workshop%3A+Eighth+Conference+on+Computational+Natural+Language+Learning)
3. Carreras, Xavier and Lluı́s Màrquez. 2005. Introduction to the CoNLL-2005 shared task: Semantic role labeling. In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), pages 152–164, Ann Arbor, MI. [our card](https://md.research.elamur.ai/free/en/papers/carreras-2005-introduction-conll-2005-shared-task/)
4. Chen, John and Owen Rambow. 2003. Use of deep linguistic features for the recognition and labeling of semantic arguments. In Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing, pages 41–48, Sapporo, Japan. [find](https://scholar.google.com/scholar?q=Chen%2C+John+and+Owen+Rambow%2E+2003%2E+Use+of+deep+linguistic+features+for+the+recognition+and+labeling+of+semantic+arguments%2E+In+Proceedings+of+the+2003+Conference+on+Empirical+Methods+in+Natural+Language)
5. Collins, Michael and Nigel Duffy. 2002. New ranking algorithms for parsing and tagging: Kernels over discrete structures, and the voted perceptron. In ACL02, pages 263–270, Philadelphia, PA. [find](https://scholar.google.com/scholar?q=Collins%2C+Michael+and+Nigel+Duffy%2E+2002%2E+New+ranking+algorithms+for+parsing+and+tagging%3A+Kernels+over+discrete+structures%2C+and+the+voted+perceptron%2E+In+ACL02%2C+pages+263%E2%80%93270%2C+Philadelphia%2C+PA%2E)
6. Culotta, Aron and Jeffrey Sorensen. 2004. Dependency tree kernels for relation extraction. In ACL04, pages 423–429, Barcelona, Spain. [our card](https://md.research.elamur.ai/free/en/papers/culotta-2004-dependency-tree-kernels-relation-extraction/)
7. Cumby, Chad and Dan Roth. 2003. Kernel methods for relational learning. In Proceedings of ICML 2003, pages 107–114, Washington, DC. [find](https://scholar.google.com/scholar?q=Cumby%2C+Chad+and+Dan+Roth%2E+2003%2E+Kernel+methods+for+relational+learning%2E+In+Proceedings+of+ICML+2003%2C+pages+107%E2%80%93114%2C+Washington%2C+DC%2E)
8. Fillmore, Charles J. 1968. The case for case. In Emmon Bach and Robert T. Harms, editors, Universals in Linguistic Theory. Holt, Rinehart, and Winston, New York, pages 1–210. [find](https://scholar.google.com/scholar?q=Fillmore%2C+Charles+J%2E+1968%2E+The+case+for+case%2E+In+Emmon+Bach+and+Robert+T%2E+Harms%2C+editors%2C+Universals+in+Linguistic+Theory%2E+Holt%2C+Rinehart%2C+and+Winston%2C+New+York%2C+pages+1%E2%80%93210%2E)
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. Haghighi, Aria, Kristina Toutanova, and Christopher Manning. 2005. A joint model for semantic role labeling. In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), pages 173–176, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Haghighi%2C+Aria%2C+Kristina+Toutanova%2C+and+Christopher+Manning%2E+2005%2E+A+joint+model+for+semantic+role+labeling%2E+In+Proceedings+of+the+Ninth+Conference+on+Computational+Natural+Language+Learning+%28CoNLL%2D20)
11. Jackendoff, Ray. 1990. Semantic Structures, Current Studies in Linguistics Series. The MIT Press, Cambridge, MA. [find](https://scholar.google.com/scholar?q=Jackendoff%2C+Ray%2E+1990%2E+Semantic+Structures%2C+Current+Studies+in+Linguistics+Series%2E+The+MIT+Press%2C+Cambridge%2C+MA%2E)
12. Joachims, Thorsten. 1999. Making large-scale SVM learning practical. In B. Schölkopf, C. Burges, and A. Smola, editors, Advances in Kernel Methods—Support Vector Learning. MIT Press, Cambridge, MA, pages 169–184. [find](https://scholar.google.com/scholar?q=Joachims%2C+Thorsten%2E+1999%2E+Making+large%2Dscale+SVM+learning+practical%2E+In+B%2E+Scho%CC%88lkopf%2C+C%2E+Burges%2C+and+A%2E+Smola%2C+editors%2C+Advances+in+Kernel+Methods%E2%80%94Support+Vector+Learning%2E+MIT+Press%2C+Cambridge%2C+MA%2C+p)
13. Kazama, Jun’ichi and Kentaro Torisawa. 2005. Speeding up training with tree kernels for node relation labeling. In Proceedings of EMNLP 2005, pages 137–144, Toronto, Canada. [find](https://scholar.google.com/scholar?q=Kazama%2C+Jun%E2%80%99ichi+and+Kentaro+Torisawa%2E+2005%2E+Speeding+up+training+with+tree+kernels+for+node+relation+labeling%2E+In+Proceedings+of+EMNLP+2005%2C+pages+137%E2%80%93144%2C+Toronto%2C+Canada%2E)
14. Kudo, Taku and Yuji Matsumoto. 2003. Fast methods for kernel-based text analysis. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 24–31, Sapporo, Japan. [find](https://scholar.google.com/scholar?q=Kudo%2C+Taku+and+Yuji+Matsumoto%2E+2003%2E+Fast+methods+for+kernel%2Dbased+text+analysis%2E+In+Proceedings+of+the+41st+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+24%E2%80%9331%2C+Sapporo%2C+Japa)
15. Levin, Beth. 1993. English Verb Classes and Alternations. The University of Chicago Press, Chicago, IL. [find](https://scholar.google.com/scholar?q=Levin%2C+Beth%2E+1993%2E+English+Verb+Classes+and+Alternations%2E+The+University+of+Chicago+Press%2C+Chicago%2C+IL%2E)
16. Lin, H.-T., C.-J. Lin, and R. C. Weng. 2003. A note on Platt’s probabilistic outputs for support vector machines. Technical report, National Taiwan University. [find](https://scholar.google.com/scholar?q=Lin%2C+H%2E%2DT%2E%2C+C%2E%2DJ%2E+Lin%2C+and+R%2E+C%2E+Weng%2E+2003%2E+A+note+on+Platt%E2%80%99s+probabilistic+outputs+for+support+vector+machines%2E+Technical+report%2C+National+Taiwan+University%2E)
17. Litkowski, Kenneth. 2004. Senseval-3 task: Automatic labeling of semantic roles. In Senseval-3: Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, pages 9–12, Barcelona, Spain. [find](https://scholar.google.com/scholar?q=Litkowski%2C+Kenneth%2E+2004%2E+Senseval%2D3+task%3A+Automatic+labeling+of+semantic+roles%2E+In+Senseval%2D3%3A+Third+International+Workshop+on+the+Evaluation+of+Systems+for+the+Semantic+Analysis+of+Text%2C+pages+9%E2%80%9312%2C)
18. Marcus, M. P., B. Santorini, and M. A. Marcinkiewicz. 1993. Building a large annotated corpus of English: The Penn treebank. Computational Linguistics, 19:313–330. [our card](https://md.research.elamur.ai/free/en/papers/marcus-1993-building-large-annotated-corpus-english/)
19. Moschitti, Alessandro. 2004. A study on convolution kernels for shallow semantic parsing. In Proceedings of the 42 th Conference on Association for Computational Linguistic (ACL-2004), pages 335–342, Barcelona, Spain. [find](https://scholar.google.com/scholar?q=Moschitti%2C+Alessandro%2E+2004%2E+A+study+on+convolution+kernels+for+shallow+semantic+parsing%2E+In+Proceedings+of+the+42+th+Conference+on+Association+for+Computational+Linguistic+%28ACL%2D2004%29%2C+pages+335%E2%80%93342%2C+)
20. Moschitti, Alessandro. 2006a. Efficient convolution kernels for dependency and constituent syntactic trees. In Proceedings of The 17th European Conference on Machine Learning, pages 318–329, Berlin, Germany. [find](https://scholar.google.com/scholar?q=Moschitti%2C+Alessandro%2E+2006a%2E+Efficient+convolution+kernels+for+dependency+and+constituent+syntactic+trees%2E+In+Proceedings+of+The+17th+European+Conference+on+Machine+Learning%2C+pages+318%E2%80%93329%2C+Berlin%2C+G)
21. Moschitti, Alessandro. 2006b. Making tree kernels practical for natural language learning. In Proceedings of 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL2006), pages 113–120, Treato, Italy. [find](https://scholar.google.com/scholar?q=Moschitti%2C+Alessandro%2E+2006b%2E+Making+tree+kernels+practical+for+natural+language+learning%2E+In+Proceedings+of+11th+Conference+of+the+European+Chapter+of+the+Association+for+Computational+Linguistics+%28E)
22. Moschitti, Alessandro, Bonaventura Coppola, Daniele Pighin, and Roberto Basili. 2005a. Engineering of syntactic features for shallow semantic parsing. In Proceedings of the ACL Workshop on Feature Engineering for Machine Learning in Natural Language Processing, pages 48–56, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Moschitti%2C+Alessandro%2C+Bonaventura+Coppola%2C+Daniele+Pighin%2C+and+Roberto+Basili%2E+2005a%2E+Engineering+of+syntactic+features+for+shallow+semantic+parsing%2E+In+Proceedings+of+the+ACL+Workshop+on+Feature+Eng)
23. Moschitti, Alessandro, Ana-Maria Giuglea, Bonaventura Coppola, and Roberto Basili. 2005b. Hierarchical semantic role labeling. In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), pages 201–204, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Moschitti%2C+Alessandro%2C+Ana%2DMaria+Giuglea%2C+Bonaventura+Coppola%2C+and+Roberto+Basili%2E+2005b%2E+Hierarchical+semantic+role+labeling%2E+In+Proceedings+of+the+Ninth+Conference+on+Computational+Natural+Language+)
24. Moschitti, Alessandro, Daniele Pighin, and Roberto Basili. 2006. Tree kernel engineering in semantic role labeling systems. In Proceedings of the Workshop on Learning Structured Information in Natural Language Applications, EACL 2006, pages 49–56, Trento, Italy. [find](https://scholar.google.com/scholar?q=Moschitti%2C+Alessandro%2C+Daniele+Pighin%2C+and+Roberto+Basili%2E+2006%2E+Tree+kernel+engineering+in+semantic+role+labeling+systems%2E+In+Proceedings+of+the+Workshop+on+Learning+Structured+Information+in+Natural)
25. Palmer, Martha, Daniel Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1): 71–106. [our card](https://md.research.elamur.ai/free/en/papers/palmer-2005-proposition-bank-annotated-corpus-semantic/)
26. Platt, J. 1999. Probabilistic outputs for support vector machines and comparison to regularized likelihood methods. In A. J. Smola, P. Bartlett, B. Schoelkopf, and D. Schuurmans, editors, Advances in Large Margin Classifiers. MIT Press, Cambridge, MA, pages 61–74. [find](https://scholar.google.com/scholar?q=Platt%2C+J%2E+1999%2E+Probabilistic+outputs+for+support+vector+machines+and+comparison+to+regularized+likelihood+methods%2E+In+A%2E+J%2E+Smola%2C+P%2E+Bartlett%2C+B%2E+Schoelkopf%2C+and+D%2E+Schuurmans%2C+editors%2C+Advances+in+)
27. Pradhan, Sameer, Kadri Hacioglu, Valerie Krugler, Wayne Ward, James H. Martin, and Daniel Jurafsky. 2005a. Support vector learning for semantic argument classification. Machine Learning, 60(1–3):11–39. [find](https://scholar.google.com/scholar?q=Pradhan%2C+Sameer%2C+Kadri+Hacioglu%2C+Valerie+Krugler%2C+Wayne+Ward%2C+James+H%2E+Martin%2C+and+Daniel+Jurafsky%2E+2005a%2E+Support+vector+learning+for+semantic+argument+classification%2E+Machine+Learning%2C+60%281%E2%80%933%29%3A11%E2%80%9339)
28. Pradhan, Sameer, Kadri Hacioglu, Wayne Ward, James H. Martin, and Daniel Jurafsky. 2005b. Semantic role chunking combining complementary syntactic views. In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), pages 217–220, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Pradhan%2C+Sameer%2C+Kadri+Hacioglu%2C+Wayne+Ward%2C+James+H%2E+Martin%2C+and+Daniel+Jurafsky%2E+2005b%2E+Semantic+role+chunking+combining+complementary+syntactic+views%2E+In+Proceedings+of+the+Ninth+Conference+on+Comp)
29. Pradhan, Sameer, Wayne Ward, Kadri Hacioglu, James Martin, and Daniel Jurafsky. 2005c. Semantic role labeling using different syntactic views. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), 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+2005c%2E+Semantic+role+labeling+using+different+syntactic+views%2E+In+Proceedings+of+the+43rd+Annual+Meeting+of+the+Associat)
30. Pradhan, Sameer S., Wayne H. Ward, Kadri Hacioglu, James H. Martin, and Dan Jurafsky. 2004. Shallow semantic parsing using support vector machines. In HLT-NAACL 2004: Main Proceedings, pages 233–240, Boston, MA. [our card](https://md.research.elamur.ai/free/en/papers/pradhan-2004-shallow-semantic-parsing-support-vector/)
31. Punyakanok, Vasin, Peter Koomen, Dan Roth, and Wen-tau Yih. 2005. Generalized inference with multiple semantic role labeling systems. In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), pages 181–184, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Punyakanok%2C+Vasin%2C+Peter+Koomen%2C+Dan+Roth%2C+and+Wen%2Dtau+Yih%2E+2005%2E+Generalized+inference+with+multiple+semantic+role+labeling+systems%2E+In+Proceedings+of+the+Ninth+Conference+on+Computational+Natural+La)
32. Shawe-Taylor, John and Nello Cristianini. 2004. Kernel Methods for Pattern Analysis. Cambridge University Press, Cambridge, UK. [find](https://scholar.google.com/scholar?q=Shawe%2DTaylor%2C+John+and+Nello+Cristianini%2E+2004%2E+Kernel+Methods+for+Pattern+Analysis%2E+Cambridge+University+Press%2C+Cambridge%2C+UK%2E)
33. Shen, Libin, Anoop Sarkar, and Aravind K. Joshi. 2003. Using LTAG based features in parse reranking. In Empirical Methods for Natural Language Processing (EMNLP), pages 89–96, Sapporo, Japan. [find](https://scholar.google.com/scholar?q=Shen%2C+Libin%2C+Anoop+Sarkar%2C+and+Aravind+K%2E+Joshi%2E+2003%2E+Using+LTAG+based+features+in+parse+reranking%2E+In+Empirical+Methods+for+Natural+Language+Processing+%28EMNLP%29%2C+pages+89%E2%80%9396%2C+Sapporo%2C+Japan%2E)
34. Thompson, Cynthia A., Roger Levy, and Christopher Manning. 2003. A generative model for semantic role labeling. In 14th European Conference on Machine Learning, pages 397–408, Cavtat, Croatia. [find](https://scholar.google.com/scholar?q=Thompson%2C+Cynthia+A%2E%2C+Roger+Levy%2C+and+Christopher+Manning%2E+2003%2E+A+generative+model+for+semantic+role+labeling%2E+In+14th+European+Conference+on+Machine+Learning%2C+pages+397%E2%80%93408%2C+Cavtat%2C+Croatia%2E)
35. Tjong Kim Sang, Erik, Sander Canisius, Antal van den Bosch, and Toine Bogers. 2005. Applying spelling error correction techniques for improving semantic role labelling. In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), pages 229–232, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Tjong+Kim+Sang%2C+Erik%2C+Sander+Canisius%2C+Antal+van+den+Bosch%2C+and+Toine+Bogers%2E+2005%2E+Applying+spelling+error+correction+techniques+for+improving+semantic+role+labelling%2E+In+Proceedings+of+the+Ninth+Con)
36. Toutanova, Kristina, Aria Haghighi, and Christopher Manning. 2005. Joint learning improves semantic role labeling. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), pages 589–596, Ann Arbor, MI. [our card](https://md.research.elamur.ai/free/en/papers/toutanova-2005-joint-learning-improves-semantic-role/)
37. Toutanova, Kristina, Penka Markova, and Christopher Manning. 2004. The leaf path projection view of parse trees: Exploring string kernels for HPSG parse selection. In Proceedings of EMNLP 2004, pages 166–173, Barcelona, Spain. [find](https://scholar.google.com/scholar?q=Toutanova%2C+Kristina%2C+Penka+Markova%2C+and+Christopher+Manning%2E+2004%2E+The+leaf+path+projection+view+of+parse+trees%3A+Exploring+string+kernels+for+HPSG+parse+selection%2E+In+Proceedings+of+EMNLP+2004%2C+pages+)
38. Vapnik, Vladimir N. 1998. Statistical Learning Theory. John Wiley and Sons, New York. [find](https://scholar.google.com/scholar?q=Vapnik%2C+Vladimir+N%2E+1998%2E+Statistical+Learning+Theory%2E+John+Wiley+and+Sons%2C+New+York%2E)
39. Vishwanathan, S. V. N. and A. J. Smola. 2002. Fast kernels on strings and trees. In Proceedings of Neural Information Processing Systems, pages 569–576, Vancouver, British Columbia. [find](https://scholar.google.com/scholar?q=Vishwanathan%2C+S%2E+V%2E+N%2E+and+A%2E+J%2E+Smola%2E+2002%2E+Fast+kernels+on+strings+and+trees%2E+In+Proceedings+of+Neural+Information+Processing+Systems%2C+pages+569%E2%80%93576%2C+Vancouver%2C+British+Columbia%2E)
40. Xue, Nianwen and Martha Palmer. 2004. Calibrating features for semantic role labeling. In Proceedings of EMNLP 2004, 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+2004%2C+pages+88%E2%80%9394%2C+Barcelona%2C+Spain%2E)
41. Zelenko, D., C. Aone, and A. Richardella. 2003. Kernel methods for relation extraction. Journal of Machine Learning Research, 3:1083–1106. [our card](https://md.research.elamur.ai/free/en/papers/zelenko-2002-kernel-methods-relation-extraction/)
42. Zhang, Min, Jie Zhang, and Jian Su. 2006. Exploring syntactic features for relation extraction using a convolution tree kernel. In Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, pages 288–295, New York, NY. [find](https://scholar.google.com/scholar?q=Zhang%2C+Min%2C+Jie+Zhang%2C+and+Jian+Su%2E+2006%2E+Exploring+syntactic+features+for+relation+extraction+using+a+convolution+tree+kernel%2E+In+Proceedings+of+the+Human+Language+Technology+Conference+of+the+NAACL%2C)