Learning to Extract International Relations from Political Context

@inproceedings{OConnor2013LearningTE,
  title={Learning to Extract International Relations from Political Context},
  author={Brendan T. O'Connor and Brandon M. Stewart and Noah A. Smith},
  booktitle={ACL},
  year={2013}
}
We describe a new probabilistic model for extracting events between major political actors from news corpora. Our unsupervised model brings together familiar components in natural language processing (like parsers and topic models) with contextual political information— temporal and dyad dependence—to infer latent event classes. We quantitatively evaluate the model’s performance on political science benchmarks: recovering expert-assigned event class valences, and detecting real-world conflict… CONTINUE READING
Highly Cited
This paper has 47 citations. REVIEW CITATIONS

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 79 references

GDELT: Global data on events, location and tone, 19792012

  • P. Schrodt, K. Leetaru
  • International Studies Association Conference.
  • 2013
Highly Influential
3 Excerpts

English Gigaword Fourth Edition

  • R. Parker, D. Graff, J. Kong, K. Chen, K. Maeda
  • Linguistic Data Consortium. LDC2009T13.
  • 2009
Highly Influential
1 Excerpt

English Gigaword Fourth Edition . Linguistic Data Consortium

  • R. Parker, D. Graff, J. Kong, K. Chen, K. Maeda
  • 2009
Highly Influential
1 Excerpt

Generalized linear models with random effects; a Gibbs sampling approach

  • S. L. Zeger, M. R. Karim
  • Journal of the American Statistical Association…
  • 1991
Highly Influential
1 Excerpt

Applications of Latent Variable Models in Modeling Influence and Decision Making

  • S. M. Gerrish
  • Ph.D. thesis, Princeton University.
  • 2013

Automatic extraction of events from open source text for predictive forecasting

  • E. Boschee, P. Natarajan, R. Weischedel
  • Handbook of Computational Approaches to…
  • 2013
1 Excerpt

Similar Papers

Loading similar papers…