[Colloquium] 1/25 Talks at TTIC: Dani Yogatama, CMU

[Mary Marre]

When:     Monday, January 25th at 11:00 am

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

Who:       Dani Yogatama, CMU

Title: Learning to Represent Language: Embeddings and Optimization

Abstract:
The performance of a machine learning model heavily depends on how the data
is represented in the model. For example, when working with text data we
can represent words as strings, binary vectors, or real vectors. Recent
advances have sought to automate these choices to save human costs and
achieve better results.

In this talk, I will first discuss how to encode prior knowledge into a
representation learning model with structured regularizers. I will present
an application of this technique to learn a word embedding model that
encourages hierarchical ordering of word meanings (e.g., "professor" is a
hyponym of "academic"). This model outperforms or is competitive with
state-of-the-art methods on standard word embedding evaluation tasks.

I will then talk about how to efficiently perform representation learning
in two real-world settings where we need to work with streams of datasets
and streams of input/output.
In the first setting, I will present a method to quickly decide how best to
represent a dataset by treating this problem as an optimization over a very
large discrete set of choices. I will show how we can use Bayesian
optimization to solve it efficiently and briefly describe an improved
Bayesian optimization algorithm that can generalize across multiple
datasets.
In the second setting, using speech recognition as an example problem, I
will discuss a representation learning method for sequential prediction
problems that supports online decoding (unidirectional recurrent neural
networks) and achieves high accuracy, allowing deployment in a live
production system.


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>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20160119/a0076ae5/attachment.htm