6.648, Qs: Transcription, Phonetics, Feedback on parser results

Sat May 6 01:45:14 UTC 1995

----------------------------------------------------------------------
LINGUIST List:  Vol-6-648. Fri 05 May 1995. ISSN: 1068-4875. Lines: 163

Subject: 6.648, Qs: Transcription, Phonetics, Feedback on parser results

Moderators: Anthony Rodrigues Aristar: Texas A&M U. <aristar at tam2000.tamu.edu>
            Helen Dry: Eastern Michigan U. <hdry at emunix.emich.edu>

Asst. Editors: Ron Reck <rreck at emunix.emich.edu>
               Ann Dizdar <dizdar at tam2000.tamu.edu>
               Ljuba Veselinova <lveselin at emunix.emich.edu>
               Annemarie Valdez <avaldez at emunix.emich.edu>

                           REMINDER
[We'd like to remind readers that the responses to queries are usually
best posted to the individual asking the question. That individual is
then  strongly encouraged to post a summary to the list.   This policy was
instituted to help control the huge volume of mail on LINGUIST; so we
would appreciate your cooperating with it whenever it seems appropriate.]

-------------------------Directory-------------------------------------

1)
Date: Tue, 2 May 95 13:06:45 -0700
From: eudaim at ella.mills.edu (Claudia Medina)
Subject: transcriptions

2)
Date: Tue, 2 May 1995 13:45:53 -0500 (CDT)
From: Mari Olsen (molsen at astrid.ling.nwu.edu)
Subject: phonetics for Korean learners of English

3)
Date:   Tue, 2 May 1995 07:50:45 -1000
From: Phil Bralich (bralich at uhunix.uhcc.Hawaii.Edu)
Subject: MORE parser results

-------------------------Messages--------------------------------------
1)
Date: Tue, 2 May 95 13:06:45 -0700
From: eudaim at ella.mills.edu (Claudia Medina)
Subject: transcriptions

Content-Length: 996

Hi!
I am writing my MA thesis about handwriting recognition.  I wanted to ask
if any of you know if there are transcribed handwritten notes available, or
markup languages used for that kind of transcription.

Thank you very much,
Claudia

--------------------------------------------------------------------------
2)
Date: Tue, 2 May 1995 13:45:53 -0500 (CDT)
From: Mari Olsen (molsen at astrid.ling.nwu.edu)
Subject: phonetics for Korean learners of English

A student of mine is developing a program to prepare Koreans for work
overseas.  Her students will need to learn English and most likely
another language, if the native language of the country they are going
to is not English.  She was wondering whether there were any
articulatory phonetics textbooks designed to teach
perception/transcription from the Korean perspective (the text I am
using in class--a ms. from Lonna Dickerson--is written for the native
Englishspeaker, introducing the English vowels and consonants first,
etc).  Please reply to me--I'll summarize if it's necessary.

Thanks.

Mari Broman Olsen
Northwestern University
Department of Linguistics
2016 Sheridan Road
Evanston, IL 60208

molsen at astrid.ling.nwu.edu
molsen at babel.ling.nwu.edu

--------------------------------------------------------------------------
3)
Date:   Tue, 2 May 1995 07:50:45 -1000
From: Phil Bralich (bralich at uhunix.uhcc.Hawaii.Edu)
Subject: MORE parser results

To the readers:
Last week I posted a message in which I presented 30 sentences which
can be correctly judged as acceptable or not by a parser that is being
developed here in Hawaii.  The parser is  based on a theory of syntax
developed by myself and Derek Bickerton.  In this message I want to
present the acceptability judgements that the parser gives for coreference.
This is of course not a complete list, but we would like to ask the
readers of this list for feedback concerning structures that they believe
would be problematic for us.  The parser is still quite young, but we are
very pleased with these early results.

Here are the specs the parser.  It is based on a series of algorithms that
have been four years in the making, but the programming required to
create this parser has only taken 300 hours using C++ .  There
are approximately 3000 lines of code that take up 150k executable on
disk.  About 100k of RAM is required to run the parser.  30k on disk is
required for a 300 word dictionary.   An average sentence takes
under 4 seconds to process on a 486 IBM compatible.  Since this is
only a development version, we expect these numbers to change.  To
date, no optimizations have occurred, and we expect to significantly
shrink the dictionary disk usage and the execution time.

The final demonstration version of the parser (due to finish in a few
weeks) will: 1) identify sentences as correct, incorrect but parsable
(e.g. John likes herself), or unparsable (e.g. John up red the), 2)
identify parts of speech as appropiate for context (correctly separating
ambiguous words such as 'can' the verb and 'can' the noun), 3) identify
parts of the sentence such as subject verb, object, (including complex
subjects and objects as in "What John knows is scary" "John's pictures
of himself are good" or "That John likes Mary is shocking."  4) change
active sentences to passive and passive to active, 5) change noun
clauses to questions and questions to noun clauses.  The parser will
also be able to identify appropriate referents for reflexives and
pronouns.  Finally, the parser will be able to respond to statements and
answer questions based on a text that you create from the 200 word
dictionary.

Here are the acceptability judgements for coreference that the parser
delivers so far:

     (1)  John1 likes himself1
     (2)  John1 showed Mary2 herself2
     (3)  *John1 showed herself2 Mary2
     (4)  John1 thought that Fred2 showed Bill3 pictures of  himself
          *1 / 2 / 3.
     (5)  John1 likes Bobs2 pictures of himself 2 / *1.
     (6)  They1 thought that the pictures of them1 / themselves1
          confused Bob.
     (9)  *John's1 mother hates himself1
     (10)  John1 told Bob2 that pictures of himself1/2 were
          available.
     (11)  John1 told Bob2 e to take pictures of himself *1/2.
     (12)  John1 likes  him*1
     (13)  John1 gave a book to him *1
     (14)  John1 likes the pictures of  him 1
     (15)  John1 likes  Bob's2 pictures of him1 2
     (16)  John1 gave a book to the man near him1
     (17)  John1 took the money with him1
     (18)  John1 threw a brick at him*1
     (19)  John1 likes himself1.
     (20)  *John1 likes him1.
     (21)   *John1 likes John1.
     (22)   *He1 likes John1
     (23)  John1 believes Mary likes him1
     (24)  *He1 believes Mary likes John1
     (25)  Who1 thinks Mary likes him1 ?
     (26)   *Who1 does he1 think  Mary1 likes e1?

If readers have any comments or suggestions for other examples, we would
appreciate hearing from you.

Thanks much

Phil Bralich
bralich at uhccux.uhcc.Hawaii.edu

--------------------------------------------------------------------------
LINGUIST List: Vol-6-648.