LINGUIST List 4.1022

Wed 01 Dec 1993

Qs: Scanners, Mayan, Native Languages, Lattice Corpus

Editor for this issue: <>

Directory

1. , scanners
2. , Quiche-Maya
3. Sheila M Shigley, Native Language Revival
4. E S Atwell, Lattice Corpus training sets requested

Do you or your readers have any knowledge of scanners that can read text
containing phonetics? Sincerely, Graham Shorrocks.

I am studying binding phenomena in Quiche. I would greatly appreciate
any information anyone has on work that has been done on this topic,
or on binding in any other Mayan language. Thank you

Seth Minkoff
MIT

Hello All...

 This is an updated version of a query I posted earlier on Linguist.
I am involved with a Native language salvage program here in Wisconsin
and would very much like to get in touch with those involved currently
in similar projects, or those who have experience (practical or
theoretical) in techniques and strategies for such projects. What I
am actually hoping for is open and continuous dialogue on this issue, and
I wonder if this might be better accomplished on the Nat-Lang list
rather than Linguist? I don't know how many here subscribe already, but
here's the address:

 Nat-langtamvm1.tamu.edu
 or
 Nat-langtamvm1.bitnet

(send subscriptions to listservtamvm1.tamu.edu or listservtamvm1.bitnet)

I posted the same query there and am looking forward to responses. There's
little to no traffic on this list right now, so if you're worried about
flooding your mailbox with Nat-lang traffic it shouldn't be a problem...at
least not until we (hopefully) get a more active subscriber base going!
Any responses to this query will be greatly appreciated, whether it be a
lengthy project description or merely "the name of someone you know who
might be interested."

 Thanks for your time,

 Sheila Shigley
 shigleymacc.wisc.edu

Please reply direct to Dan Modd, csxdtmscs.leeds.ac.uk - not me. Thanks.
 - Eric Atwell


My Computer Science final year project involves collecting together a wide
range of word-hypothesis recognition lattices, as output from large-vocabulary
speech and handwriting recognition systems. These word-candidate lattices look
something like this:

 stephen stiffen stiffens
 left lift
 school scowl scull
 lest last
 yearn your year

The collected lattices will constitute a standard Lattice Corpus which,
hopefully, could be used as an evaluation resource for research in linguistic
constraint models for English speech and handwriting recognition systems.

Initially, I need to compare the range of word-lattice formats used by language
 modelling researchers to arrive at a standard representation format.

If your research is in this area, I would be very grateful if you could send
me one or more example lattices (preferably as an ascii text file). Any
information about the format of the lattices (e.g. documentation, references,
e.t.c.) would also be welcome.

Thanks for your help,

Dan Modd
Centre for Computer Analysis of Speech and Language,
School of Computer Studies, University of Leeds.
 csxdtmscs.leeds.ac.uk