<html>
<body>
Hi Merle<br>
I must admit I hadn't been thinking of "parallel" corpora along
such strict-definition lines.<br><br>
So who is creating large amounts of 'parallel' data (in the
technical/translation sense)<br>
for British English and American English? I wouldn't have thought there
was a very large <br>
market....?<br><br>
Noah Smith mentioned Harry Potter, and I must admit I'm quite surprised
to discover <br>
that publishers are making such changes as<br>
<blockquote type=cite class=cite cite=""> They had drawn for
the house cup<br>
They had tied for the house cup</blockquote>Perhaps because
it's "children's" literature? Or at least read by many
children, <br>
who may not be willing/able to cross varietal boundaries with total
comfort.<br><br>
But when I read a novel by an American author, I accept that it's part of
my role as reader to <br>
take on board any varietal differences as part of the context. I can't
imagine anyone wanting<br>
to translate it into British English for my benefit, and I suspect I
would hate to read the resulting <br>
text...<br><br>
Best<br>
Ramesh<br><br>
<br>
At 18:53 09/11/2006, Merle Tenney wrote:<br>
<blockquote type=cite class=cite cite="">Ramesh Krishnamurthy wrote:<br>
> <br>
> ...and there is no obvious parallel corpus of Br-Am Eng to
consult...<br>
> Do you know of one by any chance...<br>
> <br>
> And Mark P. Line responded:<br>
> <br>
>Why would it have to be a *parallel* corpus?<br>
<br>
In a word, alignment. The formative work in parallel corpora has
come from the machine translation crowd, especially the statistical
machine researchers. The primary purpose of having a parallel
corpus is to align translationally equivalent documents in two languages,
first at the sentence level, then at the word and phrase level, in order
to establish word and phrase equivalences. A secondary purpose,
deriving from the sentence-level alignment, is to produce source and
target sentence pairs to prime the pump for translation memory
systems.<br>
<br>
Like you, I have wondered why you couldn't study two text corpora of
similar but not equivalent texts and compare them in their
totality. Of course you can, but is there any way in this scenario
to come up with meaningful term-level comparisons, as good as you can get
with parallel corpora? I can see two ways you might proceed:<br>
<br>
The first method largely begs the question of term equivalence. You
begin with a set of known related words and you compare their frequencies
and distributions. So if you are studying language models, you
compare <i>sheer</i>, <i>complete</i>, and <i>utter </i>as a group.
If you are studying dialect differences, you study <i>diaper</i> and
<i>nappy</i> or <i>bonnet</i> and <i>hood</i> (clothing and
automotive). If you are studying translation equivalence in English
and Spanish, you study <i>flag</i>, <i>banner</i>, <i>standard</i>,
<i>pendant</i> alongside <i>bandera</i>, <i>estandarte</i>,
<i>pabellón</i> (and <i>flag</i>, <i>flagstone</i> vs. <i>losa</i>,
<i>lancha</i>; <i>flag</i>, <i>fail,</i> <i>languish</i>, <i>weaken</i>
vs. <i>flaquear</i>, <i>debilitarse</i>, <i>languidecer</i>; etc.).
The point is, you already have your comparable sets going in, and you
study their usage across a broad corpus. One problem here is that
you need to have a strong word sense disambiguation component or you need
to work with a word sense-tagged corpus to deal with homophonous and
polysemous terms like <i>sheer</i>, <i>bonnet</i>, <i>flat</i>, and
<i>flag, </i>so you still have some hard work left even if you start with
the related word groups.<br>
<br>
The second method does not begin, a priori, with sets of related
words. In fact, generating synonyms, dialectal variants, and
translation equivalents is one of its more interesting challenges.
Detailed lexical, collocational, and syntactic characterizations is
another. Again, this is much easier to do if you are working with
parallel corpora. If you are dealing with large, nonparallel texts,
this is a real challenge. Other than inflected and lemmatized word
forms, there are a few more hooks that can be applied, including POS
tagging and WSD. Even if both of these technologies perform well,
however, that is still not enough to get you to the quality of data that
you get with parallel corpora.<br>
<br>
Mark, if you can figure out a way to combine the quality and quantity of
data from a very large corpus with the alignment and equivalence power of
a parallel corpus without actually having a parallel corpus, I will
personally nominate you for the Nobel Prize in Corpus Linguistics.
J<br>
<br>
Merle<br>
<br>
PS and Shameless Microsoft Plug: In the last paragraph, I
accidentally typed “figure out a why to combine” and I got the blue
squiggle from Word 2007, which was released to manufacturing on Monday of
this week. It suggested <i>way</i>, and of course I took the
suggestion. I am amazed at the number of mistakes that the
contextual speller has caught in my writing since I started using
it. I recommend the new version of Word and Office for this feature
alone. J</blockquote>
<x-sigsep><p></x-sigsep>
Ramesh Krishnamurthy<br><br>
Lecturer in English Studies, School of Languages and Social Sciences,
Aston University, Birmingham B4 7ET, UK<br>
[Room NX08, North Wing of Main Building] ; Tel: +44 (0)121-204-3812 ;
Fax: +44 (0)121-204-3766<br>
<a href="http://www.aston.ac.uk/lss/staff/krishnamurthyr.jsp" eudora="autourl">
http://www.aston.ac.uk/lss/staff/krishnamurthyr.jsp<br><br>
</a>Project Leader, ACORN (Aston Corpus Network):
<a href="http://corpus.aston.ac.uk/" eudora="autourl">
http://corpus.aston.ac.uk/</a></body>
</html>