21.2736, Qs: Automated Antecedent Constituency Tests

[linguist at LINGUISTLIST.ORG]

LINGUIST List: Vol-21-2736. Mon Jun 28 2010. ISSN: 1068 - 4875.

Subject: 21.2736, Qs: Automated Antecedent Constituency Tests

Moderators: Anthony Aristar, Eastern Michigan U <aristar at linguistlist.org>
            Helen Aristar-Dry, Eastern Michigan U <hdry at linguistlist.org>
 
Reviews: Monica Macaulay, U of Wisconsin-Madison  
Eric Raimy, U of Wisconsin-Madison  
Joseph Salmons, U of Wisconsin-Madison  
Anja Wanner, U of Wisconsin-Madison  
       <reviews at linguistlist.org> 

Homepage: http://linguistlist.org/

The LINGUIST List is funded by Eastern Michigan University, 
and donations from subscribers and publishers.

Editor for this issue: Danielle St. Jean <danielle at linguistlist.org>
================================================================  

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.

In addition to posting a summary, we'd like to remind people that it
is usually a good idea to personally thank those individuals who have
taken the trouble to respond to the query.

To post to LINGUIST, use our convenient web form at
http://linguistlist.org/LL/posttolinguist.cfm.

===========================Directory==============================  

1)
Date: 25-Jun-2010
From: Rose Hendricks < rohendricks at vassar.edu >
Subject: Automated Antecedent Constituency Tests
 

	
-------------------------Message 1 ---------------------------------- 
Date: Mon, 28 Jun 2010 10:28:27
From: Rose Hendricks [rohendricks at vassar.edu]
Subject: Automated Antecedent Constituency Tests

E-mail this message to a friend:
http://linguistlist.org/issues/emailmessage/verification.cfm?iss=21-2736.html&submissionid=2639334&topicid=8&msgnumber=1
  


Dear LINGUIST List subscribers, 

I am currently doing a linguistic internship at MIT, and I am working with 
a computer program that simplifies sentences by breaking them into 
smaller ones. However, the program has trouble identifying the 
antecedent of a relative clause when it is preceded by NP1 prep NP2. It 
automatically considers NP2 to be the antecedent, which is problematic 
for sentences such as: 

"It was an extremely detailed search of the vehicle which recovered 
those bullets." 

I think that if the program could identify constituents, it would 
realize that "search of the vehicle" is one, and could then identify 
"search" as the antecedent. Are there any constituency tests that do 
not require serious semantic knowledge (i.e., are there any that a 
computer program could be taught to do)? It seems that a test like "can 
it be the answer to a question?" is too complicated for a computer.

Thank you,
Rose Hendricks
Vassar College 2013 

Linguistic Field(s): Syntax
                     Text/Corpus Linguistics




-----------------------------------------------------------
LINGUIST List: Vol-21-2736