Current LTI Colloquium website

Course Information

The LTI colloquium is a series of talks related to language technologies. The topics include but are not restricted to Computational Linguistics, Machine Translation, Speech Recognition and Synthesis, Information Retrieval, Computational Biology, Machine Learning, Text Mining, Knowledge Representation, Computer-Assisted Language Learning and Intelligent Language Tutoring. To get credit of the course, students are required to write either a short critique of one of the presentations or a comparison of two.


 Fridays 2:30-3:50pm


 7500 Wean Hall


 Teruko Mitamura, teruko (at)


 Yi-Chia Wang, yichiaw (at)


UpComing talk


Dec 9, Friday, 2:30pm

Kevin Knight


Language Translation and Code-Breaking


In 1949, Warren Weaver suggested applying cryptanalysis methods to the problem of automatic language translation.  He said: "When I look at an article in Russian, I say: this is really written in English, but it has been coded in some strange symbols. I will now proceed to decode".


Weaver's inspiration has borne fruit in this century, as statistical techniques have enabled us to build translation systems for many languages, with increasing accuracy.  But other fruitful connections between code-breaking and translation are only starting to emerge.  This talk will examine some: estimating the amount of data required to break a cipher, building translation systems without parallel data, and solving a previously-undeciphered manuscript from the 1730s.



Kevin Knight is a Senior Research Scientist and Fellow at the University of Southern California's Information Sciences Institute, and a Research Professor in the Computer Science Department at USC.  He received a Ph.D. in computer science from Carnegie Mellon University and a bachelor's degree from Harvard University.  His research interests include natural language processing, statistical modeling, machine translation, language generation, and decipherment.  He currently serves as president of the Association for Computational Linguistics.



Sep 2

Alon Lavie

Statistical MT with Syntax and Morphology: Challenges and Some Solutions

Sep 9

----------SRS (No Colloquium) ----------

Sep 16

Bob Frederking

Going beyond Identifinder

Sep 23

Lori Levin

Modal Constructions in Machine Translation:
beyond propositional semantics

Sep 30

Joseph Keshet
Toyota Technological Institute at Chicago

Loss Minimization for Voice Onset Time (VOT) Measurement, Phoneme Alignment, and Phoneme Recognition

Oct 7

Huan Liu,

When Connected, Are We Still in Control of Our Destinies?

Oct 14

Ed Hovy

Toward a New Semantics:
Merging Propositional and Distributional Information

Oct 21

---------------------LTI anniversary (No Colloquium)---------------------

Oct 28

Martha Palmer
Univ of Colorado

Beyond Shallow Semantics

Nov 4

Sarah Cohen
Duke Univ.

Computation and Watchdog Journalism: Investigative Reporting Methods in the Digital Age

Nov 11

Yiming Yang

Modeling Novelty in Multi-session Retrieval

Nov 18

Michael Mauldin
Former LTI faculty

Turning your ideas into money
by taking your company public

Nov 25

---------- Thanksgiving holiday (No Colloquium) ----------

Dec 2

Larry Birnbaum Northwestern Univ.

From Contextual Search to Automatic Content Generation: Scaling Human Editorial Judgment

Dec 9

Kevin Knight

Language Translation and Code-Breaking