Publications

  • Siahbani, M., & Sarkar, A. (2014). Two Improvements to Left-to-Right Decoding for Hierarchical Phrase-based Machine Translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Doha, Qatar: Association for Computational Linguistics.
  • Siahbani, M., & Sarkar, A. (2014). Expressive Hierarchical Rule Extraction for Left-to-Right Translation. In Proceedings of the 11th Biennial Conference of the Association for Machine Translation in the Americas (AMTA-2014). Vancouver, Canada.
  • Sankaran, B., & Sarkar, A. (2014). Bayesian Iterative-cascade Framework for Hierarchical Phrase-based Translation. In Proceedings of the 11th Biennial Conference of the Association for Machine Translation in the Americas (AMTA-2014). Vancouver, Canada.
  • Dholakia, R., & Sarkar, A. (2014). Pivot-based Triangulation for Low-Resource Languages. In Proceedings of the 11th Biennial Conference of the Association for Machine Translation in the Americas (AMTA-2014). Vancouver, Canada.
  • Siahbani, M., Mehdizadeh Seraj, R., & Sarkar, A. (2014). Incremental Translation using a Hierarchical Phrase-based Translation System. In In Proceedings of the 2014 IEEE Spoken Language Technology Workshop (SLT 2014). Nevada, USA.

News

Joint Discussion with BC Cancer Agency 16 Dec 2014

In this week, Wed Dec 12th, Natlang will have a joint discussion with BC Cancer Agency. Researchers form BC Cancer Agency will present some of their IR and clustering work on PubMed and then Naltang researchers will talk about some of their approaches that combine NLP, domain adaptation and visualization.

Response-Based Online Structured Prediction by Stefan Riezler 01 Dec 2014

In the lab meeting this week, on Wed Dec 3ed, we will be hosting Stefan Riezler from Heidelberg University. He is going to give a talk about Response-Based Online Structured Prediction (with Applications to Grounded Statistical Machine Translation). The meeting will be at TASC1 9204 West 10:30am.

ABSTRACT:
In response-based structured prediction, instead of a gold-standard structure, the learner is given a response to a predicted structure. Different types of environments such as an extrinsic task, a computer program, or a human, can respond in form of a ranking, an acceptance/rejection decision, or an improvement of the predicted structures. In this talk, we present three instantiations of response-based learning scenarios for grounded statistical machine translation (SMT), where response signals are elicited by embedding SMT into cross-lingual information retrieval, into multilingual database access, and into human corrections of translations.

BIO:
Prof. Stefan Riezler has been appointed full professor and head of the chair of Linguistic Informatics at Heidelberg University in 2010, after spending a decade in the world’s most renowned industry research labs (Xerox PARC, Google). He received his PhD in Computational Linguistics from the University of Tübingen in 1998, and then conducted post-doctoral work at Brown University in 1999. Prof. Riezler’s research focus is on machine learning and statistics applied to natural language processing problems, especially for the application areas of natural-language based web search and statistical machine translation.

Singular Value Decomposition Tutorial 18 Nov 2014

The topic of the lab meeting this week, Nov 19, is Singular Value Decomposition (SVD). We will follow following tutorial loosely.
Tutorial on SVD by Kirk Baker
The meeting will be at TASC1 9408 from 1030 hours.

A Tutorial on Information Visualization 10 Nov 2014

For the lab meeting this week, 12th of Nov, Fred will provide a short tutorial on Information Visualization: Principles, Promise, and Pragmatics based on Marti Hearst’s 2003 CHI Tutorial.

Automatic Question Generation 03 Nov 2014

In the lab meeting this week, 5th of Nov, Lydia will give a talk about Automatic Question Generation, integration of a Question Generation (QG) system with a learning environment and evaluation techniques for questions generated by a QG system.. The meeting will be at TASC1 9408 from 1030 hours.