Identification and Evaluation of Keyphrases: Fuzzy Set based Scoring and Turing Test Inspired Evaluation

Automatic keyphrase extraction aims at extracting a compact representation of a single document, which can be used for numerous applications such as indexing, classi?cation or summarization. Existing keyphrase extraction approaches typically consist of two steps. An extraction step to select the candidate phrases using some heuristics and a scoring phase for ranking the extracted candidate phrases based on their importance in the text. Existing approaches to automatic keyphrase extraction mainly de?ne the set of phrases of a document as a crisp set and by scoring and ranking the phrases, they select the keyphrases of the document. In this work we de?ne the set of phrases in a document to be a fuzzy set, and based on the membership values of the phrases, we select the ones with higher membership values as the keyphrases of the document. Moreover we propose a novel evaluation method inspired by the Turing test, which can be used for extractive summarization tasks.