JASON M. EISNER
Curriculum Vitae (PDF)

Education and Honors

Professional Experience

Professional Activities

• Program chair, EMNLP-CoNLL (2007).
• President, ACL SIG for Computational Morphology and Phonology (2001-); executive committee (1998-).
• Editorial board member, Research in Language and Computation (2006-2011).
• Program chair, SIGMORPHON Workshop (2008, with Jeff Heinz); SIGPHON Workshop on Finite-State Phonology (2000).
• Problems committee, North American Computational Linguistics Olympiad (2006-2007).
• Advisory board member, cogito.org (2005-).
• Graduate program chair, CS Department, Johns Hopkins University (2002-).
• Program area chair, EMNLP (2006, for machine learning).
• Program area co-chair, HLT-NAACL (2006, for syntax/grammar/morphology).
• Program area chair, EACL (2006, for phonology/morphology/finite-state/tagging/segmentation).
• Publications chair, ACL (2005). Co-chair for HLT/NAACL Tutorial and Workshop Programs (2003).
• Special issue editor, Cognitive Science (2002).
• Journal reviewer, ACM Transactions on Speech and Language Processing (2008, 2005), Computational Linguistics (2007, 2005, 2004, 2002, 2001, 2000), Cognition (2002), IEEE Transactions on Audio, Speech, and Language Processing (2007), J. of Algorithms (1997). Language and Speech (1999), Phonology (2008), Research on Language and Computation (2008, 2007).
• Program committee for ACL (2007, 2005, 2004, 2003, 2002), COLING (2008), EACL (2006, 2003, 1999), EMNLP (2008, 2007, 2006, 2003, 2002), FSMNLP (2005, 2001), ICFP (2008), ICML (2004), MITWPL (1999), NAACL (2006), SIGMORPHON (2008, 2006, 2004, 2002, 2000, 1998), TeachCL/TNLP (2008, 2005, 2002), Formal Approaches to Slavic Linguistics 8 (1999); reviewer for IJCAI (2007).
• NSF panel reviewer (2004, 2003).
• Lecturer, NAACL Summer School in Human Language Technology (2002-).
• Member, EU/NSF joint working group: "ePhilology: Emerging Language Technologies and the Rediscovery of the Past" (2002).

Fellowships and Awards

Grants

Invited talks

• The Dyna Language. CMU and Google, May 2008; MIT, November 2006; IBM Yorktown Heights, May 2006; Microsoft Research, August 2005; University of Washington, August 2005.
• Searching for optimal permutations with very large-scale neighborhoods. JHU Applied Math & Statistics Dept., November 2007.
• Discovering syntactic deep structure via Bayesian statistics. U. of Maryland, May 2007.
• Bootstrapping Without the Boot. MITRE Corporation, August; IPAM Document Space Workshop, January 2006.
• Parameterized Finite-State Machines and Their Training. U. of Saarland, Germany, March 2004; AT&T Research, October 2002.
• Inferring Transformations. Mathematics of Language Conference (MoL8), Bloomington, 2003.
• Learning Natural-Language Grammars using a Bayesian Prior. RIT, May 2000. (Also at Johns Hopkins, February; UCLA Linguistics Dept., June 1999.)
• Doing OT in a Straitjacket. UCLA Linguistics Dept., June 1999. (Also updated versions at U. Rochester Linguistics Dept., March 2000; Johns Hopkins Cognitive Science Dept., September 2002.)
• Job talks at Stanford, UT Austin, U. Toronto, U. Rochester, U. Chicago, 1999.
• Constraining OT: Primitive Optimality Theory. MIT Linguistics Dept., April 1997.

Journal articles

• Eng, John and Jason M. Eisner (2004). Radiology Report Entry with Automatic Phrase Completion Driven by Language Modeling. Radiographics 24(5):1493-1501, September-October.
• Eisner, Jason (2002). Discovering syntactic deep structure via Bayesian statistics. Cognitive Science 26(3):255-268, May-June.
• Eisner, Jason (2002). Introduction to the special section on linguistically apt statistical methods. Cognitive Science 26(3):235-237, May-June.

Book chapters

• Eisner, Jason (2000). Bilexical grammars and their cubic-time parsing algorithms. In Harry Bunt and Anton Nijholt (eds.), Advances in Probabilistic and Other Parsing Technologies, pp. 29-62. Kluwer, October.

Edited volumes

• Eisner, Jason and Jeffrey Heinz (eds.) (2008). Proceedings of the Tenth Meeting of the ACL Special Interest Group on Computational Morphology and Phonology. Association for Computational Linguistics. 57 pp., June.
• Eisner, Jason (ed.) (2007). Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), 1220 pp., June. Association for Computational Linguistics.
• Eisner, Jason, Lauri Karttunen and Alain Thériault (eds.) (2000). Finite-State Phonology: Proceedings of the Fifth Workshop of the ACL Special Interest Group in Computational Phonology (SIGPHON), 67 pp., August. Association for Computational Linguistics.

  Book reviews

  • Eisner, Jason (2000). Review of Optimality Theory, by René Kager. Computational Linguistics 26(2):286-290, June.

  Ph.D. thesis

  • Eisner, Jason (2001). Smoothing a Probabilistic Lexicon Via Syntactic Transformations. 318 pp. University of Pennsylvania.

  Refereed conference and workshop proceedings

  • Eisner, Jason and Noah A. Smith (2008). Competitive grammar writing. Proceedings of the Third Workshop on Issues in Teaching Computational Linguistics, , Columbus, June.
  • Karakos, Damianos, Jason Eisner, Sanjeev Khudanpur, and Markus Dreyer (2008). Machine translation system combination using ITG-based alignments. Proceedings of the 2008 Conference of the Association for Computational Linguistics (ACL), , Columbus, June.
  • Smith, David A. and Jason Eisner (2007). Bootstrapping feature-rich dependency parsers with entropic priors. Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 667-677, Prague, June.
  • Zaidan, Omar, Jason Eisner, and Christine Piatko (2007). Using "annotator rationales" to improve machine learning for text categorization. Human Language Technologies: Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), pp. 260-267, Rochester, NY, April.
  • Karakos, Damianos, Jason Eisner, Sanjeev Khudanpur, and Carey E. Priebe (2007). Cross-instance tuning of unsupervised document clustering algorithms. Human Language Technologies: Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), pp. 252-259, Rochester, NY, April.
  • Karakos, Damianos, Sanjeev Khudanpur, Jason Eisner, and Carey E. Priebe (2007). Iterative denoising using Jensen-Renyi divergences with an application to unsupervised document categorization. Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), Honolulu, April.
  • Eisner, Jason and John Blatz (2007). Program transformations for optimization of parsing algorithms and other weighted logic programs. Proceedings of FG 2006: The 11th Conference on Formal Grammar, pp. 45-85. CSLI Publications.
  • Mason, Joshua, Kathryn Watkins, Jason Eisner, and Adam Stubblefield (2006). A natural-language approach to automated cryptanalysis of two-time pads. Proceedings of the ACM Conference on Computer and Communications Security (CCS), pp. 235-244, Alexandria, VA, October.
  • Eisner, Jason and John Blatz (2006). Program transformations for optimization of parsing algorithms and other weighted logic programs. Pre-proceedings of the 11th Conference on Formal Grammar (FG-2006), pp. 39-59. Superseded by longer post-proceedings version.
  • 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), pp. 317-326, Sydney, July.
  • 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.
  • 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.
  • Eisner, Jason and Roy W. Tromble (2006). Local search with very large-scale neighborhoods for optimal permutations in machine translation. Proceedings of the HLT-NAACL Workshop on Computationally Hard Problems and Joint Inference in Speech and Language Processing, pp. 57-75, New York, June.
  • 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.
  • Tromble, Roy W. and Jason Eisner (2006). A fast finite-state relaxation method for enforcing global constraints on sequence decoding. Proceedings of HLT-NAACL, pp. 423-430, New York, June.
  • 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), pp. 30-41, Vancouver, October.
  • Eisner, Jason and Damianos Karakos (2005). Bootstrapping without the boot. Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT-EMNLP), pp. 395-402, Vancouver, October.
  • Eisner, Jason, Eric Goldlust, and Noah A. Smith (2005). Compiling comp ling: Weighted dynamic programming and the Dyna language. Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT-EMNLP), pp. 281-290, Vancouver, October.
  • 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, pp. 73-82, Edinburgh, July.
  • Smith, Noah A., and Jason Eisner (2005). Contrastive estimation: Training log-linear models on unlabeled data. Proceedings of the 43rd Meeting of the Association for Computational Linguistics (ACL), pp. 354-362, Ann Arbor, Michigan, June. Nominated for best paper award.
  • Kempe, André, Jean-Marc Champarnaud, Jason Eisner, Franck Guingne, and Florent Nicart (2005). A class of rational n-WFSM auto-intersections. Proceedings of the Tenth International Conference on Implementation and Application of Automata (CIAA-2005). Lecture Notes in Computer Science 3845:189-200.
  • Kempe, Andre, Jean-Marc Champarnaud, and Jason Eisner (2004). A note on join and auto-intersection of n-ary rational relations. Proceedings of the Eindhoven FASTAR Days, pp. 64-78, December.
  • Eisner, Jason, Eric Goldlust, and Noah A. Smith (2004). Dyna: A declarative language for implementing dynamic programs. Proceedings of the 42st Meeting of the Association for Computational Linguistics (companion volume), pp. 218-221, Barcelona, July.
  • Smith, Noah A. and Jason Eisner (2004). Annealing techniques for unsupervised statistical language learning. Proceedings of the 42st Meeting of the Association for Computational Linguistics (ACL), pp. 486-493, Barcelona, July.
  • Eisner, Jason (2003). Learning non-isomorphic tree mappings for machine translation. Proceedings of the 41st Meeting of the Association for Computational Linguistics (companion volume), pp. 205-208, Sapporo, July.
  • Eisner, Jason (2003). Simpler and more general minimization for weighted finite-state automata. Proceedings of the Joint Meeting of the Human Language Technology Conference and the North American Chapter of the Association for Computational Linguistics (HLT-NAACL), pp. 64-71, Edmonton, May.
  • Eisner, Jason (2002). Parameter estimation for probabilistic finite-state transducers. Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 1-8, Philadelphia, July.
  • Eisner, Jason (2002). Comprehension and compilation in Optimality Theory. Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 56-63, Philadelphia, July.
  • Eisner, Jason (2002). An interactive spreadsheet for teaching the forward-backward algorithm. Proceedings of the ACL Workshop on Effective Tools and Methodologies for Teaching NLP and CL, pp. 10-18, Philadelphia, July.
  • Eisner, Jason (2002). Transformational priors over grammars. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), p. 63-70, Philadelphia, July. Nominated for best paper award.
  • Eisner, Jason (2001). Expectation Semirings: Flexible EM for Finite-State Transducers. Proceedings of the ESSLLI Workshop on Finite-State Methods in NLP (FSMNLP), 5 pp., Helsinki, August.
  • Eisner, Jason (2000). Easy and hard constraint ranking in Optimality Theory. Finite-State Phonology: Proceedings of the Fifth SIGPHON Workshop, pp. 22-33, Luxembourg, August.
  • Eisner, Jason (2000). Directional constraint evaluation in Optimality Theory. Proceedings of COLING-2000, pp. 257-263, Saarbrücken, Germany, August.
  • Eisner, Jason and Giorgio Satta (2000). A faster parsing algorithm for lexicalized tree-adjoining grammars. Proceedings of the 5th Workshop on Tree-Adjoining Grammars and Related Formalisms (TAG+5), pp. 14-19, Paris, May.
  • Eisner, Jason and Giorgio Satta (1999). Efficient parsing for bilexical context-free grammars and head automaton grammars. Proceedings of the 37th Annual Meeting of the ACL, pp. 457-464, College Park, Maryland, June.
  • Eisner, Jason (1997). Bilexical grammars and a cubic-time probabilistic parser. Proceedings of the International Workshop on Parsing Technologies (IWPT '97), pp. 54-65, MIT, September.
  • Eisner, Jason (1997). Efficient generation in primitive Optimality Theory. Proceedings of the 35th Annual Meeting of the ACL, pp. 313-320, Madrid, July.
  • Eisner, Jason (1997). FootForm decomposed: Using primitive constraints in OT. Proceedings of SCIL VII: MIT Working Papers in Linguistics, 31:115-143, edited by Benjamin Bruening.
  • Eisner, Jason M (1996). Three new probabilistic models for dependency parsing: An exploration. Proceedings of COLING-96, pp. 340-345, Copenhagen, August.
  • Eisner, Jason (1996). Efficient normal-form parsing for Combinatory Categorial Grammar. Proceedings of the 34th Annual Meeting of the ACL, pp. 79-86, Santa Cruz, June.
  • B. Baldwin, J.C. Reynar, M. Collins, J. Eisner, A. Ratnaparkhi, J. Rosenzweig, A. Sarkar, and B. Srinivas (1995). Description of the University of Pennsylvania entry in the MUC-6 competition. Proceedings of the Sixth Message Understanding Conference (MUC-6), pp. 177-191, Maryland, October.
  • Eisner, Jason (1995). `All'-less in Wonderland? Revisiting any. In Janet Fuller, Ho Han, and David Parkinson (eds.), Proceedings of ESCOL 11, pp. 92-103. Ithaca, NY: DMLL Publications.
  • Jones, Mark A., and Jason M. Eisner (1992). A probabilistic parser applied to software testing documents. Proceedings of National Conference on Artificial Intelligence (AAAI-92), pp. 322-328, San Jose.
  • Jones, Mark A., and Jason M. Eisner (1992). A probabilistic parser and its application. Proceedings of the AAAI-92 Workshop on Statistically-Based Natural Language Processing Techniques, pp. 20-27, San Jose.

  Refereed presentations

  • Eisner, Jason, Michael Kornbluh, Gordon Woodhull, Raymond Buse, Samuel Huang, Constantinos Michael, and George Shafer (2006). Visual navigation through large directed graphs and hypergraphs. Proceedings of the IEEE Symposium on Information Visualization (InfoVis'06), Poster/Demo Session, pp. 116-117, Baltimore, October.
  • Eisner, Jason M (1997). Pinning down Gen and Con for phonology. Hopkins Optimality Theory Workshop (poster session), Baltimore, May.
  • Eisner, Jason M (1997). What constraints should OT allow? LSA Annual Meeting, Chicago, January.

  Invited papers

• Karakos, Damianos, Sanjeev Khudanpur, Jason Eisner, and Carey E. Priebe (2005). Unsupervised classification via decision trees: An information-theoretic perspective. Proceedings of the 2005 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1081-1084, Philadelphia, March. Invited talk.

  Technical reports

  • Cui, Jia and Jason Eisner (2006). Finite-state Dirichlet allocation: Learned priors on finite-state models.. Technical Report 53, Center for Language and Speech Processing, Johns Hopkins University, April.
  • Hajic, Jan, et al. (2004). Natural language generation in the context of machine translation. Technical report, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, March. 87 pp.
  • Eisner, Jason (1997). State-of-the-Art Algorithms for Minimum Spanning Trees.. Ms. (to become TR), University of Pennsylvania, April. 78 pp.
  • Eisner, Jason M (1996). An empirical comparison of probability models for dependency grammar. Technical report IRCS-96-11, Institute for Research in Cognitive Science, Univ. of Pennsylvania. 18 pp.
  • Eisner, Jason M (1991). Indirect STV election: A voting system for South Africa. White paper, University of Cape Town, June. 16 pp.
  • Eisner, Jason M (1990). Dynamical-systems behavior in recurrent and non-recurrent connectionist nets. Undergraduate honors thesis, Harvard University, April. 57 pp.

  Outreach (general audience)

  • Eisner, Jason (2000). The science of language: Computational linguistics. Imagine Magazine, Center for Talented Youth, Johns Hopkins University, Baltimore, March.
  • Eisner, Jason (1991). Cognitive science and the search for intelligence. Invited paper presented to the Socratic Society, University of Cape Town, South Africa. 24 pp.

  Patents

  • Jeffrey C. Reynar, Fred Herz, Jason Eisner, Lyle Ungar (1996). A Lempel-Ziv data compression technique utilizing a dictionary pre-filled with frequent letter combinations, words and/or phrases. U.S. Patent #5,951,623 issued 9/14/1999.
  • Frederick Herz, Lyle Ungar, Jason M. Eisner (1996). System for the automatic determination of customized prices and promotions. Pending.
  • Frederick S. M. Herz, Jason M. Eisner, Lyle H. Ungar (1995). System for generation of object profiles for a system for customized electronic identification of desirable objects. U.S. Patent #5,835,087 issued 11/10/1998.
  • Frederick S. M. Herz, Jason M. Eisner, Lyle H. Ungar, Mitchell P. Marcus (1995). System for generation of user profiles for a system for customized electronic identification of desirable objects. U.S. Patent #5,754,939 issued 5/19/1998.
  • Frederick S. M. Herz, Jason Eisner, Marcos Salganicoff (1995). Pseudonymous server for system for customized electronic identification of desirable objects. U.S. Patent #5,754,938 issued 5/19/1998.

  Teaching

  7/2000-		Department of Computer Science, Johns Hopkins University
  	Assistant Professor and Graduate Program Chair. Robert B. Pond, Sr. Excellence in Teaching Award (Whiting School of Engineering, 2005). Natural Language Processing (2001-2004, 2006-) A mixed graduate-undergraduate class that teaches a synthesis of statistical models, formal grammars, and linguistic theory, with associated algorithms. It is reputed to be one of the most challenging classes in the Computer Science department, requiring both rigor and intellectual flexibility. Faculty at several other universities have asked to use the extensive online course materials. Enrollment: about 30. Declarative Methods (2005-) A new course for juniors, seniors, and graduate students. It surveys computational problems that tend to pop up frequently in different guises (e.g., constraint satisfaction); the specification languages used to describe instances of these problems; general toolkits for solving these instances; and the algorithms run by these toolkits. Enrollment: about 35. Seminar in Natural Language Processing (ongoing) A weekly reading and discussion group, exploring important current research in natural language processing and potentially relevant material from related fields. Topics are chosen by the group; each topic lasts 3-4 weeks. Attendance: up to 10 (not all enrolled). Totally Random (2004, 2005) A 4-class discussion unit about random numbers and the uses of randomness in computer science. Part of the department's new freshman experience course. Enrollment: 8-10. Data Structures (2003, 2004) A sophomore-level class, the third and last in the programming sequence for majors. Covers basic data structures and algorithms, basic analysis of algorithms, and object-oriented programming style. Online "warmups" and highly interactive classes stimulated the students to come up with designs and variations. The challenging weekly assignments often used real-world data. Faculty at a dozen other universities have asked to use the course materials. Enrollment: about 50. Finite-State Methods in Natural Language Processing (2000-2001) A graduate class on semiring-weighted finite-state transducers. Covers theory and practice, including the theory of formal power series, the extended regular expression calculus, and a range of applications to natural language. Rigorous assignments. Attendance: about 20 (mostly not enrolled). Statistical Language Learning (2002) A graduate class about past and present research that has attempted, with mixed success, to induce the structure of language from raw data such as text. Lectures are intermixed with reading and discussion of the primary literature. Attendance: about 10 (mostly not enrolled).
  2002-		Lecturer, NAACL Summer School in Human Language Technology
  1/2000-6/2001		Department of Computer Science, University of Rochester
  	Assistant Professor. Statistical Learning of Natural Language (2000) (see Statistical Language Learning, above) Graduate Problem Seminar (2000) Boot camp for new Ph.D. students. Students learn research skills by teaming up to tackle a series of open-ended engineering problems that touch on research in the department. (I made them build systems for face orientation detection, distributed calendar management, and information retrieval.) Several written and oral presentations are required and receive extensive feedback. The class also includes career advice, familiarization with departmental resources, presentations by other faculty, and a final research project. Enrollment: 10.
  1994-95		Department of Computer Science, University of Pennsylvania
  	TA in Introduction to Programming. Graduate Teaching Award.

  Advising

  Ph.D. students

  • Nathaniel W. Filardo (2007-)
  • Jason A. Smith (2006-)
  • Omar Zaidan (2005-)
  • John Blatz (2004-)
  • Eric Goldlust (2004-2005) (Wolman Fellow; Muuss Research Award; Hon. Mention for CRA Outstanding Undergraduate Award)
  • Markus Dreyer (2003-) (Wolman Fellow)
  • David A. Smith (2002-) (NSF Fellow)
  • Roy Tromble (2002-) (NSDEG Fellow)
  • Noah A. Smith (2001-2006) (Hertz Foundation Fellow; now Asst. Prof., CMU)

  B.S/M.S.E. research students

  • Wren Thornton (2008-)
  • Asheesh Laroia (2006-2007)
  • Samuel Huang (2006-2007) (Pistritto Fellow)
  • Constantinos Michael (2005-2006)
  • George Shafer (2005-2006)
  • John Graettinger (2005-2006) (Outstanding Research Award)
  • Michael Kornbluh (2004-2005) (Pistritto Fellow, Outstanding Senior Award)
  • Chalaporn Hathaidharm (2002-2004)

  Ph.D. thesis committees

  • Sara Finley (2008)
  • Jia Cui (2008)
  • Mark Thober (2007)
  • Gaja Jarosz Snover (2006)
  • Jonathan Allen (2006)
  • Gideon Mann (2006)
  • Charles Schafer (2006)
  • Myroslava Dzikovska (2004, Univ. of Rochester)
  • Silviu Cucerzan (2003)
  • Radu "Hans" Florian (2002)
  • Jun Wu (2002)
  • Richard Wicentowski (2002)
  • Grace Ngai (2000)