Replication of the Keyword Extraction part of the paper "'Without the Clutter of Unimportant Words': Descriptive Keyphrases for Text Visualization"
This is an incremental replication study focusing on keyword extraction for text visualization, which may aid in summarizing diverse text sources.
The paper replicates a keyword extraction study to test three hypotheses for identifying descriptive keyphrases, aiming to improve text summarization for large datasets like emails and social media posts, but does not report specific numerical results.
"Keyword Extraction" refers to the task of automatically identifying the most relevant and informative phrases in natural language text. As we are deluged with large amounts of text data in many different forms and content - emails, blogs, tweets, Facebook posts, academic papers, news articles - the task of "making sense" of all this text by somehow summarizing them into a coherent structure assumes paramount importance. Keyword extraction - a well-established problem in Natural Language Processing - can help us here. In this report, we construct and test three different hypotheses (all related to the task of keyword extraction) that take us one step closer to understanding how to meaningfully identify and extract "descriptive" keyphrases. The work reported here was done as part of replicating the study by Chuang et al. [3].