Seminar on Computational Learning and
Adaptation
Learning
to Identify Semantic Roles
Cindi
Thompson
PriceWaterhouseCoopers
Identifying and classifying the key semantic components of a sentence
or phrase is an important part of determining sentence
meaning. We present a model of natural language generation from
semantics using the FrameNet semantic role and frame ontology. We
present a learning approach for identifying semantically relevant
components of a syntactic parse, using its class labels to help train a
generative model for role labeling. The model is trained in a
novel manner to identify both roles and irrelevant components.
Our model makes fewer assumptions than prior models applied to the
task, and it produces results competitive with previous work.
Portions of this research were done jointly, with Chris Manning and
others, when the speaker was a Visiting
Professor at Stanford.
|
Date: Wednesday, February 9, 2005
|
Time: 4:15-5:30PM
|
Place: Gates 104
|
Co-sponsored by the Natural
Language and Speech Processing Colloquium.
Return to the seminar schedule