UTCS Colloquium/AI: Rebecca Hwa/University of Pittsburgh: Learning Evaluation Metrics for Sentence-Level Machine-Translation ACES 2.402 Friday October 17 2008 11:00 a.m.

Contact Name: 
Jenna Whitney
Oct 17, 2008 11:00am - 12:00pm

There is a signup schedule for this event (UT EID required).


e of Talk: UTCS Colloquium/AI

Speaker/Affiliation: Rebecca Hwa/Uni

versity of Pittsburgh

Date/Time: Friday October 17 2008 11:00 a.m


Location: ACES 2.402

Host: Ray Mooney

Talk Title:<

br>Learning Evaluation Metrics for Sentence-Level Machine-Translation
Talk Abstract:
The field of machine translation (MT) has made

r strides in recent years. An important enabling
factor has been the ad

option of automatic evaluation
metrics to guide researchers in making i

to their systems. Research in automatic evaluation

ics faces two major challenges. One is to achieve
higher agreement with
human judgments when
evaluating MT outputs at the sentence-level. Anot

is to minimize the reliance on expensive human-developed

rces such as reference sentences. In this talk I
present a regression-

based approach to metric development.
Our experiments suggest that by c

ombining a wide range
of features the resulting metric has higher corr

elations with
human judgments. Moreover we show that the features do <

br>not have to be extracted from comparisons with human
produced refere

nces. Using weaker indicators of fluency
and adequacy our learned metr

ics rival standard reference-
based metrics in terms of correlations wit

h human judgments
on new test instances.

Speaker Bio:
Hwa is an Assistant Professor in the Department
of Computer Science at
the University of Pittsburgh. Her
research focus is on multilingual pr

ocessing machine
translation and semi-supervised learning methods. Be

joining Pitt she was a postdoctoral research fellow at the

iversity of Maryland. She received her PhD from Harvard
University and

her B.S. from UCLA.