[Colloquium] REMINDER: 8/10 Thesis Defense: Hao Tang, TTIC

[Mary Marre via Colloquium]

When:    Thursday, August 10th at 1:00 pm

Where:   TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526

Who:      Hao Tang, TTIC


Title:       Sequence Prediction with Neural Segmental Models

Abstract:
Segments that span contiguous parts of inputs, such as phonemes in
speech, named entities in sentences, actions in videos, occur
frequently in sequence prediction problems.  Segmental models, a class
of models that explicitly hypothesizes segments, have allowed the
exploration of rich segment features for sequence prediction.
However, segmental models suffer from slow decoding, hampering the use
of computationally expensive features.  In addition, training
segmental models requires detailed manual annotation, which makes
collecting data expensive.

In the first part of the talk, I will introduce discriminative
segmental cascades, a multi-pass inference framework that allows us to
improve accuracy by adding higher-order features and neural segmental
features while maintaining efficiency.  In the second part of the
talk, I will discuss end-to-end training for segmental models with
various loss functions, and show how end-to-end training can eliminate
the need for detailed manual annotation.  I will present a unifying
framework for various end-to-end sequence prediction models, such as
hidden Markov models, connectionist temporal classification, and
segmental models. Finally, I will discuss possible extensions of
segmental models to large vocabulary sequence prediction tasks.


Thesis Advisor: Karen Livescu <klivescu at ttic.edu>


Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*

On Thu, Aug 3, 2017 at 4:50 PM, Mary Marre <mmarre at ttic.edu> wrote:

> When:    Thursday, August 10th at 1:00 pm
>
> Where:   TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>
> Who:      Hao Tang, TTIC
>
>
> Title:       Sequence Prediction with Neural Segmental Models
>
> Abstract:
> Segments that span contiguous parts of inputs, such as phonemes in
> speech, named entities in sentences, actions in videos, occur
> frequently in sequence prediction problems.  Segmental models, a class
> of models that explicitly hypothesizes segments, have allowed the
> exploration of rich segment features for sequence prediction.
> However, segmental models suffer from slow decoding, hampering the use
> of computationally expensive features.  In addition, training
> segmental models requires detailed manual annotation, which makes
> collecting data expensive.
>
> In the first part of the talk, I will introduce discriminative
> segmental cascades, a multi-pass inference framework that allows us to
> improve accuracy by adding higher-order features and neural segmental
> features while maintaining efficiency.  In the second part of the
> talk, I will discuss end-to-end training for segmental models with
> various loss functions, and show how end-to-end training can eliminate
> the need for detailed manual annotation.  I will present a unifying
> framework for various end-to-end sequence prediction models, such as
> hidden Markov models, connectionist temporal classification, and
> segmental models. Finally, I will discuss possible extensions of
> segmental models to large vocabulary sequence prediction tasks.
>
>
> Thesis Advisor: Karen Livescu <klivescu at ttic.edu>
>
>
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 504*
> *Chicago, IL  60637*
> *p:(773) 834-1757 <(773)%20834-1757>*
> *f: (773) 357-6970 <(773)%20357-6970>*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20170809/fc0ebfdb/attachment.html>