Managing Lexical Ambiguity in the Generation of Referring Expressions
Imtiaz Hussain Khan, Muhammad Haleem · International Journal of Intelligent Systems and Applications · 2013
Most existing algorith ms for the Generation of Referring Expressions (GRE) tend to produce distinguishing descriptions at the semantic level, disregarding the ways in wh ich surface issues (e.g.linguistic ambiguity) can affect their quality.In this article, we high light limitations in an existing GRE algorith m that takes lexical ambiguity into account, and put forward some ideas to address those limitat ions.The proposed ideas are imp lemented in a GRE algorith m.We show that the revised algorith m successfully generates optimal referring exp ressions without greatly increasing the computational co mplexity of the (original) algorithm.