From huiyang at cs.cmu.edu  Mon May 11 13:28:22 2009
From: huiyang at cs.cmu.edu (Grace Hui Yang)
Date: Mon, 11 May 2009 13:28:22 -0400
Subject: [IR Series] - Hua Ai - Friday, May 15 2009, noon - NSH 3002
Message-ID: <4A086036.3090707@cs.cmu.edu>

Greetings,

Please join us for our IR-Series talk this Friday noon!  Lunch will be 
provided by Yahoo!.

Speaker: Hua Ai (Intelligent Systems Program at University of Pittsburgh)

Date/Time: Friday May 15, 2009, noon
Location: 3002 Newell-Simon Hall (NSH)

User Simulation for Spoken Dialog System Development

Abstract:
In this talk, I will present my thesis study on investigating how to
evaluate and how to build user simulations to help dialog system
development. When evaluating user simulations, I use both human judges and
automatic evaluation measures to assess the simulation model qualities.
When building user simulations, I examine three factors that impact
simulation models in the tasks of dialog strategy learning and dialog
system development.

The talk is based on the author's ACL 2009 paper.

Grace, Jaime & Jon

From huiyang at cs.cmu.edu  Thu May 14 16:21:06 2009
From: huiyang at cs.cmu.edu (Grace Hui Yang)
Date: Thu, 14 May 2009 16:21:06 -0400
Subject: [IR Series] - Hua Ai - Friday, May 15 2009, noon - NSH 3002
In-Reply-To: <4A086036.3090707@cs.cmu.edu>
References: <4A086036.3090707@cs.cmu.edu>
Message-ID: <4A0C7D32.7080206@cs.cmu.edu>

Just a reminder for tomorrow's IR-series.

> Greetings,
>
> Please join us for our IR-Series talk this Friday noon!  Lunch will be 
> provided by Yahoo!.
>
> Speaker: Hua Ai (Intelligent Systems Program at University of Pittsburgh)
>
> Date/Time: Friday May 15, 2009, noon
> Location: 3002 Newell-Simon Hall (NSH)
>
> User Simulation for Spoken Dialog System Development
>
> Abstract:
> In this talk, I will present my thesis study on investigating how to
> evaluate and how to build user simulations to help dialog system
> development. When evaluating user simulations, I use both human judges 
> and
> automatic evaluation measures to assess the simulation model qualities.
> When building user simulations, I examine three factors that impact
> simulation models in the tasks of dialog strategy learning and dialog
> system development.
>
> The talk is based on the author's ACL 2009 paper.
>
> Grace, Jaime & Jon
>


From huiyang at cs.cmu.edu  Tue May 26 11:43:25 2009
From: huiyang at cs.cmu.edu (Grace Hui Yang)
Date: Tue, 26 May 2009 11:43:25 -0400
Subject: [IR Series] - Kai-min Kevin Chang - Friday, May 29 2009, noon - NSH
	1507
Message-ID: <4A1C0E1D.2090309@cs.cmu.edu>

Greetings,

 Please join us for our IR-Series talk this Friday noon!  Lunch will be 
provided by Yahoo!.

  Speaker: Kai-min Kevin Chang (Language Technologies Institute, School 
of Computer Science, Carnegie Mellon University)
  Time & Date: Friday May 29, 2009, noon.
  Place: NSH 1507 (Note the room is not the usual NSH 3002)
    
  Title: Quantitative modeling of the neural representation of 
adjective-noun phrases to account for fMRI activation
 
  Abstract:  
   Recent advances in functional Magnetic Resonance Imaging (fMRI) offer 
a significant new approach to studying semantic representations in 
humans by making it possible to directly observe brain activity while 
people comprehend words and sentences. In this study, we investigate how 
humans comprehend adjective-noun phrases (e.g. strong dog) while their 
neural activity is recorded. Classification analysis shows that the 
distributed pattern of neural activity contains sufficient signal to 
decode differences among phrases. Furthermore, vector-based semantic 
models can explain a significant portion of systematic variance in the 
observed neural activity. Multiplicative composition models of the 
two-word phrase outperform additive models, consistent with the 
assumption that people use adjectives to modify the meaning of the noun, 
rather than conjoining the meaning of the adjective and noun.

   This talk is based on the author's ACL 2009 paper.

Grace, Jon & Jaime

From huiyang at cs.cmu.edu  Thu May 28 14:39:49 2009
From: huiyang at cs.cmu.edu (Grace Hui Yang)
Date: Thu, 28 May 2009 14:39:49 -0400
Subject: [IR Series] - Kai-min Kevin Chang - tomorrow, May 29 2009, noon
	- NSH 1507
In-Reply-To: <4A1C0E1D.2090309@cs.cmu.edu>
References: <4A1C0E1D.2090309@cs.cmu.edu>
Message-ID: <4A1EDA75.2050206@cs.cmu.edu>

Just a reminder that tomorrow noon we will have Kevin's  IR-series talk.

See you then!


Grace Hui Yang wrote:
> Greetings,
>
> Please join us for our IR-Series talk this Friday noon!  Lunch will be 
> provided by Yahoo!.
>
>  Speaker: Kai-min Kevin Chang (Language Technologies Institute, School 
> of Computer Science, Carnegie Mellon University)
>  Time & Date: Friday May 29, 2009, noon.
>  Place: NSH 1507 (Note the room is not the usual NSH 3002)
>     Title: Quantitative modeling of the neural representation of 
> adjective-noun phrases to account for fMRI activation
>
>  Abstract:    Recent advances in functional Magnetic Resonance Imaging 
> (fMRI) offer a significant new approach to studying semantic 
> representations in humans by making it possible to directly observe 
> brain activity while people comprehend words and sentences. In this 
> study, we investigate how humans comprehend adjective-noun phrases 
> (e.g. strong dog) while their neural activity is recorded. 
> Classification analysis shows that the distributed pattern of neural 
> activity contains sufficient signal to decode differences among 
> phrases. Furthermore, vector-based semantic models can explain a 
> significant portion of systematic variance in the observed neural 
> activity. Multiplicative composition models of the two-word phrase 
> outperform additive models, consistent with the assumption that people 
> use adjectives to modify the meaning of the noun, rather than 
> conjoining the meaning of the adjective and noun.
>
>   This talk is based on the author's ACL 2009 paper.
>
> Grace, Jon & Jaime
>