Annotating and Learning Compound Noun Semantics
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact NLIP Seminars.
There is little consensus on a standard experimental design for the
compound noun interpretation task. I’ll introduce well-motivated general
desiderata for semantic annotation schemes, and describe such a scheme
for in-context compound annotation. A dual-annotator annotation
experiment has yielded good agreement given the difficulty of the task.
Classification experiments on an open-text dataset compare favourably
with previously reported results on other datasets and provide a solid
baseline for future research (which I’ll also briefly mention).
This talk is part of the NLIP Seminar Series series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|