The Parsed Part

This page is in progress.

The ultimate goal is to provide a version of the transcripts from the Audio Part which are Part-of-Speech Tagged, and Parsed. These transcripts will be searchable using CorpusSearch.

For now, we provide the user with a 60,000-word Part-of-Speech Tagged prototype, from the Joseph Hall collection of interviews:

http://csearch2.ling.upenn.edu/APPALACHIAN/querypos.shtml

One of our goals is to have the output of queries done on the “parsed” part to be linked up to the “audio-aligned” part, so that researchers can readily access the speech signal for the results of their parsing queries.¬†Look for updates around November¬†2017, which is the projected publication date for the AAPCAppE.