bioe_encoding.py

def get_sequence_labels(sentences, phrases):
    labels = [['O' for word in sent] for sent in sentences]
    
    for idx in range(len(sentences)):
        sent, phrase = sentences[idx], phrases[idx]

        for chunk in phrase:
            n = len(chunk)

            for start in range(len(sent)-n+1):
                if sent[start:start+n] == chunk:
                    if n == 1:
                        labels[idx][start] = 'B'
                    else:
                        labels[idx][start+1:start+n-1] = ['I']*(n-2)
                        labels[idx][start] = 'B'
                        labels[idx][start+n-1] = 'E'
    
    return labels