A Global Joint Model for Semantic Role Labeling
@article{Toutanova2008AGJ, title={A Global Joint Model for Semantic Role Labeling}, author={Kristina Toutanova and A. Haghighi and Christopher D. Manning}, journal={Computational Linguistics}, year={2008}, volume={34}, pages={161-191} }
We present a model for semantic role labeling that effectively captures the linguistic intuition that a semantic argument frame is a joint structure, with strong dependencies among the arguments. We show how to incorporate these strong dependencies in a statistical joint model with a rich set of features over multiple argument phrases. The proposed model substantially outperforms a similar state-of-the-art local model that does not include dependencies among different arguments. We evaluate the… CONTINUE READING
Topics from this paper
154 Citations
A Global Generative Model for Chinese Semantic Role Labeling
- Computer Science
- NLPCC
- 2014
- Highly Influenced
- PDF
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling
- Computer Science
- CoNLL
- 2017
- 84
- Highly Influenced
- PDF
Generative models for syntactic and semantic structure prediction using latent variables
- Computer Science
- 2015
- Highly Influenced
- PDF
Multilingual Joint Parsing of Syntactic and Semantic Dependencies with a Latent Variable Model
- Computer Science
- Computational Linguistics
- 2013
- 60
- PDF
CMILLS: Adapting Semantic Role Labeling Features to Dependency Parsing
- Computer Science
- SemEval@NAACL-HLT
- 2015
- 4
- PDF
References
SHOWING 1-10 OF 28 REFERENCES
The Proposition Bank: An Annotated Corpus of Semantic Roles
- Computer Science
- Computational Linguistics
- 2005
- 2,258
- PDF
Discriminative Reranking for Natural Language Parsing
- Computer Science
- Computational Linguistics
- 2005
- 755
- PDF
Deep Dependencies from Context-Free Statistical Parsers: Correcting the Surface Dependency Approximation
- Computer Science
- ACL
- 2004
- 75
- PDF
A Robust Combination Strategy for Semantic Role Labeling
- Computer Science
- HLT/EMNLP
- 2005
- 21
- Highly Influential
- PDF
Support Vector Learning for Semantic Argument Classification
- Computer Science
- Machine Learning
- 2005
- 295
- Highly Influential
- PDF