EMNLP 2015: Conference on Empirical Methods in Natural Language Processing — September 17–21, 2015 — Lisbon, Portugal.

emnlp2015

Invited Speakers

September 19, 2015

September 20, 2015

Talk Descriptions

Deep Learning of Semantic Representations

Yoshua Bengio

September 19, 2015

Abstract:

The core ingredient of deep learning is the notion of distributed representation. This talk will start by explaining its theoretical advantages, in comparison with non-parametric methods based on counting frequencies of occurrence of observed tuples of values (like with n-grams). The talk will then explain how having multiple levels of representation, i.e., depth, can in principle give another exponential advantage. Neural language models have been extremely successful in recent years but extending their reach from language modeling to machine translation is very appealing because it forces the learned intermediate representations to capture meaning, and we found that the resulting word embeddings are qualitatively different. Recently, we introduced the notion of attention-based encoder-decoder systems, with impressive results on machine translation several language pairs and for mapping an image to a sentence, and these results will conclude the talk.

Yoshua Bengio, Full Professor, Université de Montréal:

top of the page

Measuring How Elected Officials and Constituents Communicate

Justin Grimmer

September 20, 2015

Abstract:

This talk will show how elected officials use communication to cultivate support with constituents, how constituents express their views to elected officials, and why biases in both kinds of communication matter for political representation. To demonstrate the bias and its effects, I propose to use novel collections of political texts and new text as data methods. Using the new data and methods, I will show how the incentives of communication contribute to perceptions of an angry public and vitriolic politicians. Among elected officials, the ideologically extreme members of Congress disproportionately participate in policy debates, resulting in political debates that occur between the most extreme members of each party. Among constituents, the most ideologically extreme and angry voters disproportionately contact their member of Congress, creating the impression of a polarized and vitriolic public. The talk will explain how the findings help us to understand how representation occurs in American politics, while also explaining how computational tools can help address questions in the social sciences.

Justin Grimmer, Associate Professor, Stanford University:

top of the page