[Colloquium] Re: REMINDER: 2/17 Talks at TTIC: Karl Stratos, Bloomberg

[Mary Marre via Colloquium]

When:     Friday, February 17th at 11:00 am

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

Who:       Karl Stratos, Bloomberg


Title:  Spectral Learning of Lexical Representations in Natural Language
Processing

Abstract:
There has recently been much success in deriving rich, distributional
representations of words from large quantities of unlabeled text. They
include discrete representations such as agglomerative clusters (e.g.,
Brown clusters) and real-valued vectors such as word embeddings (e.g.,
Word2Vec). These lexical representations can be deployed off-the-shelf in a
wide range of language processing tasks to help the model generalize at the
word level.

In this talk, I will present simple and efficient algorithms for learning
such representations. The algorithms are spectral; that is, they involve
the use of singular value decomposition (SVD) or similar factorization. We
show that these algorithms have several merits. Theoretically, they come
with a guarantee of recovering the underlying model given enough data.
Empirically, they deliver competitive lexical representations while often
being much more scalable (e.g., 10x faster than the Brown et al. clustering
algorithm in wall-clock time).


Host: Kevin Gimpel <kgimpel 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, Feb 16, 2017 at 5:45 PM, Mary Marre <mmarre at ttic.edu> wrote:

> When:     Friday, February 17th at 11:00 am
>
> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>
> Who:       Karl Stratos, Bloomberg
>
>
> Title:  Spectral Learning of Lexical Representations in Natural Language
> Processing
>
> Abstract:
> There has recently been much success in deriving rich, distributional
> representations of words from large quantities of unlabeled text. They
> include discrete representations such as agglomerative clusters (e.g.,
> Brown clusters) and real-valued vectors such as word embeddings (e.g.,
> Word2Vec). These lexical representations can be deployed off-the-shelf in a
> wide range of language processing tasks to help the model generalize at the
> word level.
>
> In this talk, I will present simple and efficient algorithms for learning
> such representations. The algorithms are spectral; that is, they involve
> the use of singular value decomposition (SVD) or similar factorization. We
> show that these algorithms have several merits. Theoretically, they come
> with a guarantee of recovering the underlying model given enough data.
> Empirically, they deliver competitive lexical representations while often
> being much more scalable (e.g., 10x faster than the Brown et al. clustering
> algorithm in wall-clock time).
>
>
> Host: Kevin Gimpel <kgimpel 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>*
>
> On Fri, Feb 10, 2017 at 11:31 AM, Mary Marre <mmarre at ttic.edu> wrote:
>
>> When:     Friday, February 17th at 11:00 am
>>
>> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>>
>> Who:       Karl Stratos, Bloomberg
>>
>>
>> Title:  Spectral Learning of Lexical Representations in Natural Language
>> Processing
>>
>> Abstract:
>> There has recently been much success in deriving rich, distributional
>> representations of words from large quantities of unlabeled text. They
>> include discrete representations such as agglomerative clusters (e.g.,
>> Brown clusters) and real-valued vectors such as word embeddings (e.g.,
>> Word2Vec). These lexical representations can be deployed off-the-shelf in a
>> wide range of language processing tasks to help the model generalize at the
>> word level.
>>
>> In this talk, I will present simple and efficient algorithms for learning
>> such representations. The algorithms are spectral; that is, they involve
>> the use of singular value decomposition (SVD) or similar factorization. We
>> show that these algorithms have several merits. Theoretically, they come
>> with a guarantee of recovering the underlying model given enough data.
>> Empirically, they deliver competitive lexical representations while often
>> being much more scalable (e.g., 10x faster than the Brown et al. clustering
>> algorithm in wall-clock time).
>>
>>
>> Host: Kevin Gimpel <kgimpel 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/20170217/6f2ecf09/attachment.html>