[Ltg] [Cltprogs] [Clt] LTG Seminar[PACLING Practice Presentations 2007-09-10, E6A 357, 11am]

[Marc Tilbrook]

Monday's really are not good for me, it should read:

     Monday, 10th September , 2007, 11am

----- Original Message ----- 
From: "Marc Tilbrook" <marct at ics.mq.edu.au>
To: <ltg at ics.mq.edu.au>
Sent: Monday, September 10, 2007 10:27 AM
Subject: Re: [Cltprogs] [Clt] [Ltg] LTG Seminar[PACLING Practice
Presentations 2007-09-10, E6A 357, 11am]


> Sorry about the typo, the date and time should read:
>
>     Monday, 9th September , 2007, 11am
>
> ----- Original Message ----- 
> From: "Marc Tilbrook" <marct at ics.mq.edu.au>
> To: <ltg at ics.mq.edu.au>
> Sent: Monday, September 10, 2007 1:31 AM
> Subject: [Cltprogs] [Clt] [Ltg] LTG Seminar [PACLING Practice
Presentations
> 2007-09-10, E6A 357, 11am]
>
>
> > ----
> >    LTG Seminar
> >     - see: http://www.clt.mq.edu.au/Events/Seminars.html
> >
> >     Monday, 3rd September , 2007, 10am
> >     Macquarie University, E6A, Room 357
> > ----
> >
> >    ----
> >     * Please note we are back to our 11am start.
> >    ----
> >
> > We will be having two PACLING practice presentations, by Stephen Wan and
> > Mary Gardiner.
> >
> >
> > Title: Global Revision in Summarisation: Generating Novel Sentences with
> > Prim's Algorithm
> > Speaker: Stephen Wan
> >
> > Abstract:
> > In abstract-like summarisation, extracted sentences containing key
content
> > are often revised to improve the coherence of the overall summary. In
this
> > work, we consider the task of Global Revision, in which a key sentence
is
> > revised and supplemented with additional content from the original
> > document. Specifically, this task comprises two subtasks: selecting
> > content; and grammatically ordering content, the focus of this paper.
> > Using statistical dependency models, we search for a Maximal Spanning
> > (Dependency) Tree that structures recycled words and phrases
> > to form a novel sentence. Combining a modified version of Prim's
algorithm
> > with a four-gram language model, we evaluated our system on a sentence
> > regeneration task obtaining Bleu scores of .30, a statistically
> > significant improvement above the baseline.
> >
> > ------
> >
> > Title: TBA
> > Speaker: Mary Gardiner
> >
> > Abstract:
> > TBA
> >
> >
> > _______________________________________________
> > LTG mailing list
> > LTG at ics.mq.edu.au
> > http://www.ics.mq.edu.au/mailman/listinfo/ltg
> > _______________________________________________
> > CLT mailing list
> > CLT at ics.mq.edu.au
> > http://www.ics.mq.edu.au/mailman/listinfo/clt
> > _______________________________________________
> > CLTProgs mailing list
> > CLTProgs at ics.mq.edu.au
> > http://www.ics.mq.edu.au/mailman/listinfo/cltprogs
> >
>
>
> _______________________________________________
> LTG mailing list
> LTG at ics.mq.edu.au
> http://www.ics.mq.edu.au/mailman/listinfo/ltg
> _______________________________________________
> CLT mailing list
> CLT at ics.mq.edu.au
> http://www.ics.mq.edu.au/mailman/listinfo/clt
> _______________________________________________
> CLTProgs mailing list
> CLTProgs at ics.mq.edu.au
> http://www.ics.mq.edu.au/mailman/listinfo/cltprogs
>