To do's - Githubissues

ethanweed / CHAT-transcript-tools

some scripts for working with transcripts in CHAT format

0 stars 0 forks source link

To do's #1

Open ethanweed opened 5 years ago

ethanweed commented 5 years ago

[ ] Write script to find missing %mor lines
[ ] Write script to label %mor lines with speaker ID
[ ] Wrap up scripts into functions
[ ] Wrap up functions into a CHAT transcript class

ethanweed commented 4 years ago

add to MLU function:

    # make a list with only the POS lines from the transcript
    utt = []
    for s, val in enumerate(text):
        if val.startswith('*CHI'):
            m = str(text[s+1])
            if m.startswith('%xmor'):
                m = m[5:]
                utt.append(m)