[seminarios-mlpb] Reminder: Seminar talk tomorrow

From: Miguel Almeida <miguel.almeida@xxxxxxxxxxx>
To: "seminarios-mlpb@xxxxxxxxxxxxx" <seminarios-mlpb@xxxxxxxxxxxxx>
Date: Mon, 23 Mar 2015 09:47:57 +0000
Hello all,

Tomorrow we will have Dr. Diamantino Caseiro from Google, presenting a seminar 
called "Bottleneck Neural Network Language Models".

See you there!
Miguel

********************************************************************
TALK ANNOUNCEMENT  --  Anfiteatro do Complexo Interdisciplinar
********************************************************************

Priberam Machine Learning Lunch Seminar
Speaker: Dr. Diamantino Caseiro, Google
Venue: IST Alameda, Anfiteatro do Complexo Interdisciplinar
Date: Tuesday, March 24th, 2015
Time: 13:00
Lunch will be provided


Title:
Bottleneck Neural Network Language Models

Abstract:
In the last few years, language modeling techniques based on  exponential 
models have consistently outperformed traditional n-gram models. Such 
techniques include L1-Regularized Maximum Entropy (L1-MaxEnt), and both 
Feedforward and Recurrent Neural Network  Language Models (RNNLM). While more 
accurate, these models are also much more expensive to train and use. This 
presents a problem for low latency applications where it is desirable to find 
n-gram approximations that can be used in the first pass of a speech 
recognition system. In this talk I will present Bottleneck Neural Network 
Language Models, a novel feedforward architecture designed to be achieve low 
perplexity while allowing for n-gram approximations. This model is similar to 
MaxEnt models in the sense that its input is a rich set of features, however 
these features are processed though a non linear hidden layer to encourage 
generalization. In the talk, I will compare this architecture to other 
exponential models and I will present an effective algorithm for creating 
n-gram approximations. Results will be presented on standard data sets and on a 
voice-mail to text state of the art ASR system.

Bio:
Diamantino Caseiro received a M.Sc. degree in electrical and computer 
engineering from Instituto Superior Tecnico (IST), Lisbon, Portugal in 1998, 
and a Ph.D in computer science, also from IST, in 2003. He was an assistant 
professor in the computer engineering department of this University from 2004 
to 2007 and a member of the Spoken Language Systems Laboratory of INESC-ID from 
1996 to 2007, where he specialized in weighted finite-state transducers and 
search algorithms for automatic speech recognition (ASR).  From 2008 to 2014, 
he was a Principal Research Scientist at AT&T Labs Research, being responsible 
for language modeling, finite-state transducers and search for ASR. Since 2014 
he has been a Senior Research Scientist at Google, working on search for ASR 
and on massive scale maximum entropy language modeling.

********************************************************************
General info about our seminars:  
http://labs.priberam.com/Academia-Partnerships/Seminars.aspx
Please forward this link to whoever might be interested in attending the 
seminars.


Miguel Almeida

Research Scientist

[cid:image001.png@01D0654E.7071B920]

Email: mba@xxxxxxxxxxx<mailto:mba@xxxxxxxxxxx>
URL: http://labs.priberam.com
[seminarios-mlpb] Reminder: Seminar talk tomorrow

Other related posts:
