log in  |  register  |  feedback?  |  help  |  web accessibility
Logo
Seond Languages as Meaning Annotation
Marine Carpuat - National Research Council Canada
Tuesday, September 16, 2014, 11:00 am-12:00 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
Abstract

In this talk, I will describe my recent work based on the idea that human translations into a second language can provide preexisting meaning annotations for natural language
understanding tasks, and in particular for machine translation. In contrast to manually curated representations of word meaning, translated text is readily available in large amounts
and avoids the need for costly annotation by human experts.

For example, I will show that viewing translations as word meaning annotation can help (a) design better models for machine translation, such as discriminative translation lexicons
that can select accurate translations in context, (b) improve automatic evaluation of machine translation, and (c) improve the portability of translation systems across domains.

While my past work shows that the "translation as meaning" paradigm is effective for words and short phrases, my future work aims to use second language supervision to compose the
meaning of words into complete sentences and coherent discourse. This includes investigating how to leverage more diverse sources of multilingual data as noisy supervision for natural language
understanding.

Bio

I am a researcher at the National Research Council Canada <http://www.nrc-cnrc.gc.ca/eng/ibp/iit/about/gatineau.html>. I work on computational linguistics, natural language processing and statistical machine translation. I design computational models that leverage multilingual data to understand word meaning in context, and aim to build translation systems that are more accurate, more robust and more useful.

Before moving to NRC, I was a postdoctoral researcher at the Columbia University Center for Computational Learning Systems <http://www.ccls.columbia.edu/>, working primarily with Mona Diab <http://www1.ccls.columbia.edu/%7Emdiab>. I received a PhD in Computer Science <http://www.cs.ust.hk/> from the Hong Kong University of Science & Technology <http://www.ust.hk/> in 2008. My advisor was Dekai Wu <http://www.cs.ust.hk/%7Edekai>. I also earned a MPhil in Electrical Engineering <http://www.ece.ust.hk/> from HKUST under the supervision of Pascale Fung <http://www.ece.ust.hk/%7Epascale>, and an engineering degree from the French Grande Ecole Supélec <http://www.supelec.fr/>. I did my undergraduate studies in France, at Sainte Geneviève <http://www.bginette.com/> and Supélec <http://www.supelec.fr/>.

This talk is organized by Adelaide Findlay