f00bbc9ca76a4a1fd9ddc46954a76237ecd4c616,iky_server/try.py,,extract_chunks,#Any#,16

Before Change

    grp1, grp2 = "",""
    for s, tp in tagged_sent:
        if tp != "O":
            if tp.endswith(chunk_type):
                if not tp.startswith("B"):
                    grp2 = tp
                    grp1.append(s)
                else:
                    if grp1:
                        yield " ".join(grp1), "-".join(grp2)
                    grp1, grp2 = [s], [str(ind)]
    yield " ".join(grp1), grp2

l = [("my", "o"), ("name", "B-DOMAIN"), ("is", "o"), ("Alfred", "B-NAME"),
 ("Francis", "I-NAME")]

After Change

def extract_chunks(tagged_sent):
    labeled = {}
    labels=[]
    for s, tp in tagged_sent:
        if tp != "O":
            label = tp[2:]
            if tp.startswith("B"):
                labeled[label] = s
            elif tp.startswith("I") and (label not in labels) :
                labels.append(label)
                labeled[label] = s
            elif (tp.startswith("I") and (label in labels)):
                labeled[label] += " %s"%s
    return labeled

l = [("sms", "B-TSK"), ("8714349616", "B-MOB"), ("saying", "I-MSG"), ("hello", "I-MSG"), ("how", "I-MSG"), ("are", "I-MSG"), ("you", "I-MSG")]

Instances