NEXT Oren Etzioni, Mausam, and Stephen Soderland Towards Panlingual Translation: Supporting Translations Across All Languages May 16 (Friday) Details ...

News: Want to get email notices of events? Subscribe. Interested in giving a Turing Talk? Have an existing event you think we should list? Contact the Events Committee. Want an appointment to meet with any of our visitors? Contact Patrick Allen.

Computational Linguistics Lab Discussions

Various topics in computational linguistics
Current topic schedule
For details about each meeting in advance, subscribe.
Tuesdays, 2:30 pm - 3:30 pm, Paul G. Allen Center for Computer Science and Engineering 128

Natural Language Processing Reading Group

Current paper schedule
Thursdays, 4:30 pm - 5:30 pm, Electrical Engineering M406

Machine Translation Reading Group

Recent papers in primarily statistical machine translation
Current paper schedule
Mondays, 4:00 pm - 5:00 pm, Electrical Engineering M306

Colloquium

Mausam (Turing Center) and Stephen Soderland (Turing Center)
Towards Panlingual Translation: Supporting Translations Across All Languages
February 12 (Tuesday), 3:30 pm - 5:00 pm, Electrical Engineering 105

Abstract

The goal of our project is a system that can translate between arbitrary pairs of languages. Unfortunately, most machine translation methodologies assume aligned corpora or grammar rules, which are available for only a small number of major language pairs. This makes scaling the popular approaches to any-language translation virtually impossible. We propose to scale machine translation to a panlingual level by first attempting to solve the lexical translation problem and then proceeding to translating pairs of words, phrases and then sentences. In this talk we primarily describe a novel approach to lexical translation that employs probabilistic inference over the Translation Graph, a novel lexical resource that combines translations from hundreds of machine readable dictionaries and Wiktionaries. Our inference algorithm opens up several interesting and challenging future directions that we detail in the talk. We will also demo PanImages (http://www.panimages.org), an image search application that uses the Translation Graph.

Symposium

Fourteenth UW/Microsoft Quarterly Symposium in Computational Linguistics
February 15 (Friday), 3:30 pm - 5:30 pm, Gowen 201

You are invited to take advantage of this opportunity to connect with the computational linguistics community at Microsoft and the University of Washington. Sponsored by the UW Departments of Linguistics, Electrical Engineering, and Computer Science; Microsoft Research; and UW alumni at Microsoft. The symposium consists of two invited talks, followed by a poster presentation and an informal reception.

Amar Subramanya and Jeff Bilmes (Electrical Engineering)
Training Speech Recognizers with Uncertain Word Boundaries

Colin Cherry (NLP group, Microsoft Research)
Cohesive Phrase-Based Decoding for Statistical Machine Translation

Michael Tepper (Linguistics)
Knowledge-Lite Induction of Underlying Morphology (KLIUM)

Symposium

Fifteenth UW/Microsoft Quarterly Symposium in Computational Linguistics
June 6 (Friday), 3:30 pm - 5:30 pm, Microsoft Corporation

You are invited to take advantage of this opportunity to connect with the computational linguistics community at Microsoft and the University of Washington. Sponsored by the UW Departments of Linguistics, Electrical Engineering, and Computer Science; Microsoft Research; and UW alumni at Microsoft. The symposium consists of two invited talks, followed by demonstrations and an informal reception.

NEXT

Colloquium Oren Etzioni, Mausam, and Stephen Soderland (Turing Center) Towards Panlingual Translation: Supporting Translations Across All Languages May 16 (Friday), 3:30 pm - 5:00 pm, Sieg 225 Abstract The goal of our project is a system that can translate between arbitrary pairs of languages. Unfortunately, most machine translation methodologies assume aligned corpora or grammar rules, which are available for only a small number of major language pairs. This makes scaling the popular approaches to any-language translation virtually impossible. We propose to scale machine translation to a panlingual level by first attempting to solve the lexical translation problem and then proceeding to translating pairs of words, phrases and then sentences. In this talk we primarily describe a novel approach to lexical translation that employs probabilistic inference over the Translation Graph, a novel lexical resource that combines translations from hundreds of machine readable dictionaries and Wiktionaries. We hope to also discuss whether the Graph can be used to support linguistics research, and to unearth new observations by providing lexical data on a large number of languages in concert.