Home

The LTI Student Research Symposium (SRS) is a one-day series of talks and poster presentations designed both to increase awareness of the diverse aspects of language technologies research conducted by students within the LTI, as well as to introduce incoming LTI students to the work of current students.
One of the talks will be selected for a "Best Presentation Award", which will be announced at the end of the Symposium. The winner of the "Best Presentation Award" will receive a cash prize of $500. Additionally, two Honorable Mentions will be selected, each receiving a cash prize of $100, and two $100 for "Best Poster Award" will also be presented.
An oral presentation in the Symposium fulfills the yearly presentation requirement and the speaking requirement for LTI PhD and MS students.

 2014 Program Schedule
Thursday, August 21, 2014 
Time: 10:00 am - 4:30 pm
GHC 6115  

Keynote Speaker: Dr. Andrew Moore
Dean of the School of Computer Science at Carnegie Mellon University

 
 Time Title   Presenters
10:00 am - 10:10 am Welcome and Introduction to The 2014 LTI SRS                         Florian Metze
 Oral Session I  
10:10 am - 10:35 amUnsupervised Dependency Parsing with Transferring Distribution via Parallel Guidance and Entropy RegularizationXuezhe Ma and Fei Xia 
10:35 am - 11:00 amDiversity in dependency parsingSwabha Swayamdipta, Sam Thomson and Jeffrey Flanigan
11:00 am - 11:25 amContext-Aware Word Vectors using Substitute Word DistributionsVolkan Cirik and Deniz Yuret
11:25 am - 11:50 amUnsupervised Phrasal Near-Synonym Generation from Text CorporaDishan Gupta, Jaime Carbonell and Anatole Gershman 
11:50 am - 1:20 pmLunchtacular Awesomeness 
12:15 pm - 1:20 pmAn Epic Session of Hyperactive Poster Pandemonium  
 Oral Session II 
1:20 pm - 1:45 pmQuestion Recommendation with Constraints for Massive Open Online CoursesDiyi Yang, David Adamson and Carolyn Rose 
1:45 pm - 2:10 pmDeep Semantic Topic ModelingZhiting Hu, Zaiqing Nie and Gang Luo 
2:10 pm - 2:35 pmQuery Expansion with FreebaseChenyan Xiong and Jamie Callan 
2:35 pm - 3:00 pmAutomatic Gloss Finding for a Knowledge Base using Ontological ConstraintsBhavana Dalvi, Einat Minkov, Partha Talukdar and William Cohen 
3:00 pm - 3:30 pmCoffee Break - Get Your Afternoon Caffeine Fix Here... And Prepare For... 
3:30 pm - 4:15 pmKeynote Speech "Andrew Moore reveals which is better: Academia or Industry" Andrew Moore
4:15 pm - 4:30 pmPrize Distribution and Closing RemarksFlorian Metze

Hyperactive Poster Pandemonium 2014 - The LTIghtning Round!

 Title Presenter(s)
Who negatively influences me? Formalizing diffusion dynamics of negative exposure leading to student attrition in MOOCsTanmay Sinha
Optimality Theoretic Modeling of Lexical BorrowingYulia Tsvetkov
Parsing Without Words or POS Tags: Dense Word Vectors Capture Sufficient Syntactic InformationVolkan Cirik, Hüsnü Şensoy and Deniz Yuret
Noise Robust Speaker Identification: Enhanced Cepstral Coefficients and Pitch Transition with Exhaustive Model Training
Soo Jin Park, Tiancheng Zhao, Pavel Bondarenko and Abeer Alwan
Structure Learning via Parameter LearningWilliam Yang Wang, Kathryn Mazaitis and William W Cohen
Viral Video Style: A Closer Look at Viral Videos on YouTubeLu Jiang
Language Identification for Code-Switched Tweets with CRF AutoencoderChu-Cheng Lin and Waleed Ammar





Subpages (2): Contacts Goals