DATE: | Thu, Nov 12, 2015 |
TIME: | 1:30 pm |
PLACE: | SITE 5084 |
TITLE: | Several Deep-Learning Models for Semantic Composition |
PRESENTER: |
Xiaodan Zhu NRC |
ABSTRACT:
Modeling the meaning of words and sentences is core to NLP.
In this talk, I discuss several neural-net models we developed recently,
including models that consider both compositional and non-compositional
semantics to estimate the meaning of a sentence.
I will also discuss several specific architectures, i.e., LSTMs with tree
and DAG (directed acyclic graph) structures, which achieved
state-of-the-art performance on two semantic composition tasks.
|