SCS Undergraduate Thesis Topics

Nitin Seemakurty Anthony Tomasic/Luis von Ahn Human-powered Word Sense Disambiquation

One formidable problem in language technology is disambiguating the "sense" of a word as it occurs in a sentence. For example, distinguishing "bank" as a river bank or as a financial institution. This work explores a specific strategy for solving this problem; the strategy involves harnessing the semantic abilities of human beings to develop datasets that can be used to train machine learning algorithms.

Close this window