Users

From Dyna
Jump to: navigation, search

We will make some effort to list publications and sites that use Dyna. Please help by adding to this page.

Published papers using Dyna

(See also our separate list of publications that are specifically about Dyna.)

The following somewhat old papers were not about Dyna, but they used the initial Dyna prototype for implementation. After a hiatus of a few years, we are now working on Dyna version 2.

  • [1] Smith, David A. (2010). Efficient Inference for Trees and Alignments: Modeling Monolingual and Bilingual Syntax with Hard and Soft Constraints and Latent Variables. Ph.D. dissertation, Johns Hopkins University.
  • [2] Smith, David A. and Jason Eisner (2008). Dependency parsing by belief propagation. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 145-156, Honolulu, October.
  • [3] D. Karakos, J. Eisner, S. Khudanpur and M. Dreyer (2008). Machine translation system combination using ITG-based alignments. Proceedings of the 2008 Conference of the Association for Computational Linguistics (ACL-08: HLT), Short Papers, pages 81-84. Columbus, Ohio, June.
  • [4] Smith, Noah A., Douglas L. Vail, and John D. Lafferty (2007). Computationally Efficient M-Estimation of Log-Linear Structure Models. Proceedings of ACL, pp. 752-759, Prague, June.
  • [5] Dreyer, Markus and Jason Eisner (2006). Better Informed Training of Latent Syntactic Features. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Sydney, Australia.
  • [6] Smith, David A. and Jason Eisner (2006). Minimum-risk annealing for training log-linear models. Proceedings of the International Conference on Computational Linguistics and the Association for Computational Linguistics (COLING-ACL), Companion Volume, pp. 787-794, Sydney, July.
  • [7] Smith, Noah A. and Jason Eisner (2006). Annealing structural bias in multilingual weighted grammar induction. Proceedings of the International Conference on Computational Linguistics and the Association for Computational Linguistics (COLING-ACL), pp. 569-576, Sydney, July.
  • [8] Dreyer, Markus, David A. Smith, and Noah A. Smith (2006). Vine Parsing and Minimum Risk Reranking for Speed and Precision. Proceedings of the Conference on Natural Language Learning (CoNLL), New York, June. The Dyna code for methods used in this paper is available here.
  • [9] Smith, David A. and Jason Eisner (2006). Quasi-synchronous grammars: Alignment by soft projection of syntactic dependencies. Proceedings of the HLT-NAACL Workshop on Statistical Machine Translation, pp. 23-30, New York, June.
  • [10] Schafer, Charles (2006). Novel Probabilistic Finite-State Transducers for Cognate and Transliteration Modeling. 7th Biennial Conference of the Association for Machine Translation in the Americas (AMTA).
  • [11] Schafer, Charles (2006). Translation discovery using diverse similarity measures. Doctoral dissertation. Johns Hopkins University, 2006.
  • [12] Eisner, Jason, and Noah A. Smith (2005). Parsing with soft and hard constraints on dependency length. Proceedings of the International Workshop on Parsing Technologies (IWPT), Vancouver, October. 12 pages.
  • [13] Smith, Noah A., David A. Smith, and Roy W. Tromble (2005). Context-based morphological disambiguation with random fields. Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT-EMNLP), Vancouver, October.
  • [14] Smith, Noah A. and Jason Eisner (2005). Guiding unsupervised grammar induction using contrastive estimation. International Joint Conference on Artificial Intelligence (IJCAI) Workshop on Grammatical Inference Applications, Edinburgh, July. 10 pages.
  • [15] Smith, Noah A. and Jason Eisner (2005). Contrastive estimation: Training log-linear models on unlabeled data. Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL), pages 354-362, Ann Arbor, Michigan, June.
  • [16] Smith, Noah A. and Jason Eisner (2004). Annealing techniques for unsupervised statistical language learning. Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL), pages 486-493, Barcelona, July.
  • [17] Smith, David A. and Noah A. Smith. (2004). "Bilingual parsing with factored estimation: Using English to parse Korean." In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 49-56, Barcelona.

Courses using Dyna

Dyna has been used in teaching two classes at Johns Hopkins:

  • Roy Tromble and Noah Smith co-taught a course on biological sequence modeling in fall 2004. Dyna was used to implement tools for building, training, and testing profile hidden Markov models for multiple sequence alignment and phylogeny.
  • Jason Eisner's annual course on declarative methods in computer science (first taught in spring 2005) includes a unit on Dyna. It includes some lecture slides and a hands-on assignment. This material is likely to expand.

Other users of Dyna

You can join the user discussion list by downloading Dyna.

Dyna is being used in other ongoing research projects at Johns Hopkins.

Several folks at other universities and in industry have expressed interest in using Dyna for research and teaching.

Personal tools
Namespaces

Variants
Actions
Navigation
Tools