From: bayan abu shawar <bshawar@comp.leeds.ac.uk>
Subject: Re: [Corpora-List] Does anybody know a classified faq
collection?
Cc: CORPORA@UIB.NO
In-Reply-To: <Pine.LNX.4.60.0505162156110.24868@cslin-gps.csunix.comp.le
eds.ac.uk>
References: <004d01c55a23$857994a0$97c451c2@itri.bton.ac.uk>
<004d01c55a23$857994a0$97c451c2@itri.bton.ac.uk>
Mime-Version: 1.0
Content-Type: multipart/alternative;
boundary="=====================_1228592140==_.ALT"
X-checked-clean: by exiscan on rolf
X-Scanner: 90e4bf44a66e1a14428395d533be5792 http://tjinfo.uib.no/virus.html
X-UiB-SpamFlag: NO UIB: 0.5 hits, 8.0 required
X-UiB-SpamReport: spamassassin found;
0.0 BODY: HTML included in message
0.5 BODY: Message is 20% to 30% HTML
--=====================_1228592140==_.ALT
Content-Type: text/plain; charset="us-ascii"; format=flowed
Dear all,
I am sorry that it is too late to reply, but It may be useful to any one,
according to the FAQ, FAQchat is another tool to access FAQ database, where
the input is a question and the answer is either a direct one, or links to
related answers. The process is similar to the information retrieval. For
more details read the GLDV05 from my web page: www.comp.leeds.ac.uk/bshawar.
There are a lot of ways for retrieving answers automatically:
Dumais, S., Banko, M., Brill, E., Lin, J., and Ng, A. (2002). Web question
answering: is more always better?. In Proceedings of the 25th Annual
International ACM SIGIR Conference on Research and Development in
Information Retrieval. (SIGIR 2002). Tempere, Finland, pp. 291-298.
Costello, F. and Smeaton, A. (2004). Question-Answering Systems. [Online]:
http://www.computing.dcu.ie/~away/PROJ3/00-01/lenehan.html
Kwok, C., Etzioni, O., and S.Weld, D. (2001). Scaling question answering to
the web. ACM Transcations on Information Systems. Vol. 19, No.3, pp. 242-262.
Katz, B. (1997). From sentence processing to information access on the
World Wide Web. In Natural Language Processing for the World Wide Web:
papers from the 1997 AAAI Spring Symposium, pp. 77-94.
Hopefully this is useful
Bayan Abu Shawar
School of Computing
University of Leeds
At 22:06 16/05/2005 +0100, Eric Atwell wrote:
>Ling,
>
>I don't know of a FAQ collection classified according to your preferred
>semantic classes, but there are plenty of FAQ websites whcih you could
>trawl to collect your own corpus. For example, the language of the FAQ
>of Leeds University School of Computing http://www.comp.leeds.ac.uk/faq
>is used as a Corpus in:
>
>Abu Shawar, Bayan; Atwell, Eric. A chatbot system as a tool to animate a
>corpus. to appear in ICAME Journal, vol. 29, pp. 5-24. 2005
>
>We couldnt find any standards for FAQ structure or analysis whcih applied
>across a wide range of FAQ websites; so please let us see your analysis
>results when you've finished :-)
>
>Eric Atwell, Leeds University (pp Bayan Abu Shawar)
>
>
>On Mon, 16 May 2005, Ling Yin wrote:
>
>>Dear all,
>>
>> I am studying relationships between different parts of a topic
>>expression and different discourse constituencies (the theme/rheme
>>distinction covered by information structure theory). Instead of using a
>>collection of aligned topics and discourses, I plan to use a collection
>>of frequent asked questions (FAQs). Here I take a question as a topic
>>expression and the answer as a disourse on the topic. Can anybody
>>provide a faq collection (preferably classified according to semantic
>>classes such as definitional, procedural and causal)?
>>
>> Please also tell me if you know a document collection with
>>annotated information structure or a system which does such annotation
>>automaticall.
>>
>> Thanks in advance!
>>
>>Ling
>
>--
>Eric Atwell, Senior Lecturer, Computer Vision and Language research group,
>School of Computing, University of Leeds, LEEDS LS2 9JT, England
>TEL: +44-113-2335430 FAX: +44-113-2335468 http://www.comp.leeds.ac.uk/eric
--=====================_1228592140==_.ALT
Content-Type: text/html; charset="us-ascii"
<html>
--=====================_1228592140==_.ALT--
This archive was generated by hypermail 2b29
: Wed Aug 03 2005 - 14:49:33 MET DST
Dear all,<br>
I am sorry that it is too late to reply, but It may be useful to any one,
according to the FAQ, FAQchat is another tool to access FAQ database,
where the input is a question and the answer is either a direct one, or
links to related answers. The process is similar to the information
retrieval. For more details read the GLDV05 from my web page:
<a href="http://www.comp.leeds.ac.uk/bshawar" eudora="autourl"><font color="#0000FF"><u>www.comp.leeds.ac.uk/bshawar</a></u></font>.<br><br>
There are a lot of ways for retrieving answers automatically:<br><br>
<font face="Times New Roman, Times"><b>Dumais, S., Banko, M., Brill, E.,
Lin, J., and Ng, A.</b> (2002). Web question answering: is more always
better?. In <i>Proceedings of the
25</font><font face="Times New Roman, Times" size=1><sup>th</sup></font><font face="Times New Roman, Times">
Annual International ACM SIGIR Conference on Research and Development in
Information Retrieval. (SIGIR 2002).</i> Tempere, Finland, pp.
291-298.<b> <br><br>
Costello, F. and Smeaton, A.</b> (2004). <i>Question-Answering
Systems</i>. [Online]:
</font><a href="http://www.computing.dcu.ie/~away/PROJ3/00-01/lenehan.html" eudora="autourl"><font face="Times New Roman, Times" color="#0000FF"><u>http://www.computing.dcu.ie/~away/PROJ3/00-01/lenehan.html></u></font><font face="Times New Roman, Times"><b>
<br><br>
Kwok, C., Etzioni, O., and S.Weld, D. (2001). </b>Scaling question
answering to the web. <i>ACM Transcations on Information Systems</i>.
Vol. 19, No.3, pp. 242-262.<b> <br><br>
</font>Katz, B. (1997). </b>From sentence processing to information
access on the World Wide Web.<b> </b>In Natural Language <i>Processing
for the World Wide Web: papers from the 1997 AAAI Spring Symposium</i>,
pp. 77-94.<br><br>
Hopefully this is useful<br>
Bayan Abu Shawar<br>
School of Computing<br>
University of Leeds<br><br>
At 22:06 16/05/2005 +0100, Eric Atwell wrote:<br>
<blockquote type=cite class=cite cite>Ling,<br><br>
I don't know of a FAQ collection classified according to your
preferred<br>
semantic classes, but there are plenty of FAQ websites whcih you could
trawl to collect your own corpus. For example, the language of the
FAQ<br>
of Leeds University School of Computing
<a href="http://www.comp.leeds.ac.uk/faq" eudora="autourl">http://www.comp.leeds.ac.uk/faq><br>
is used as a Corpus in:<br><br>
Abu Shawar, Bayan; Atwell, Eric. A chatbot system as a tool to animate
a<br>
corpus. to appear in ICAME Journal, vol. 29, pp. 5-24. 2005<br><br>
We couldnt find any standards for FAQ structure or analysis whcih applied
across a wide range of FAQ websites; so please let us see your analysis
results when you've finished :-)<br><br>
Eric Atwell, Leeds University (pp Bayan Abu Shawar)<br><br>
<br>
On Mon, 16 May 2005, Ling Yin wrote:<br><br>
<blockquote type=cite class=cite cite>Dear all,<br><br>
I am studying relationships between
different parts of a topic<br>
expression and different discourse constituencies (the theme/rheme<br>
distinction covered by information structure theory). Instead of using
a<br>
collection of aligned topics and discourses, I plan to use a
collection<br>
of frequent asked questions (FAQs). Here I take a question as a
topic<br>
expression and the answer as a disourse on the topic. Can anybody<br>
provide a faq collection (preferably classified according to
semantic<br>
classes such as definitional, procedural and causal)?<br><br>
Please also tell me if you know a document
collection with<br>
annotated information structure or a system which does such
annotation<br>
automaticall.<br><br>
Thanks in advance!<br><br>
Ling<br>
</blockquote><br>
-- <br>
Eric Atwell, Senior Lecturer, Computer Vision and Language research
group,<br>
School of Computing, University of Leeds, LEEDS LS2 9JT, England<br>
TEL: +44-113-2335430 FAX: +44-113-2335468
<a href="http://www.comp.leeds.ac.uk/eric" eudora="autourl">http://www.comp.leeds.ac.uk/eric></blockquote><br>
</html>