Recursive Deep Learning for Modeling Semantic Compositionality

Richard Socher 
Stanford

Great progress has been made in natural language processing thanks to many
different algorithms, each often specific to one application. Most algorithms
force language into simplified representations such as bag-of-words or
fixed-sized windows or require human-designed features. I will introduce two
general models based on recursive neural networks that can learn
linguistically plausible representations of language. These methods jointly
learn compositional features and grammatical sentence structure for parsing or
phrase level sentiment predictions. Besides the state-of-the-art performance,
the models capture interesting phenomena in language such as compositionality.
For instance, people easily see that the "with" phrase in "eating spaghetti
with a spoon" specifies a way of eating whereas in "eating spaghetti with some
pesto" it specifies the dish. I show that my model solves these prepositional
attachment problems well thanks to its distributed representations. In
sentiment analysis, a new tensor-based recursive model learns different types
of high level negation and how they can change the meaning of longer phrases
with many positive words. They also learn that when contrastive conjunctions
such as "but" are used the sentiment of the phrases following them usually
dominates.

Bio:

Richard Socher is a PhD student at Stanford working with Chris Manning and
Andrew Ng. His research interests are machine learning for NLP and vision. He
is interested in developing new deep learning models that learn useful
features, capture compositional structure in multiple modalities and perform
well across different tasks. He was awarded the 2011 Yahoo! Key Scientific
Challenges Award, the Distinguished Application Paper Award at ICML 2011, a
Microsoft Research PhD Fellowship in 2012 and a 2013 "Magic Grant" from the
Brown Institute for Media Innovation.