Suggestions from Steven Bird:

<P>I guess there's a sequence of three readings that might set the scene
for an interesting discussion on language technologies for endangered
languages.
<BR>
	1. Why collecting bilingual texts on a large scale is a good idea: The
Human Language Project: Building a universal corpus of the World's
languages <A HREF=http://repository.unimelb.edu.au/10187/7146>
(Abney & Bird, ACL 2010)</A>

<BR>
	2. How to do such collection for a small language: A scalable method
for preserving oral literature from small languages 
<A HREF=http://repository.unimelb.edu.au/10187/7141>
(Bird, ICADL 2010)</A>
<BR>
	3. Some ideas about language technologies to support this (Bird, LiLT 2010?)
<BR>
<!-- 

The first two are (also) available here: <A HREF=http://stevenbird.me/writing.html>http://stevenbird.me/writing.html</A>
<BR>
The third should be available by the start of the fall term, surely :)
<b><font color=red>[Not available as of 9/20/2010, though.]</font></b>

<P>
    By the way, are any of you going to ICLDC in Hawaii in February?  (I
saw Robert there last time).  That's a great place for hearing about
technology for language documentation, though no language technology
really.  See my Last Words piece for comments about that: Natural
Language Processing and Linguistic Fieldwork (Bird, CL 2009).
	 <A HREF=http://www.aclweb.org/anthology-new/J/J09/J09-3007.pdf>
http://www.aclweb.org/anthology-new/J/J09/J09-3007.pdf</A>
  -->