nipunsadvilkar/pySBD

Example not working with Spacy version 3.1 and 3.0.6

Atul997 opened this issue · 3 comments

I have installed current spacy version 3. 1 and running the example with some modifications but it keeps throwing error of
ValueError: [E030] Sentence boundaries unset. You can add the 'sentencizer' component to the pipeline with: nlp.add_pipe('sentencizer'). Alternatively, add the dependency parser or sentence recognizer, or set sentence boundaries by setting doc[i].is_sent_start.

Below is the code that I am using-
import spacy
import pysbd
from spacy.language import Language

@Language.component("sbd")
def pysbd_sentence_boundaries(doc):
seg = pysbd.Segmenter(language="en", clean=False, char_span=True)
sents_char_spans = seg.segment(doc.text)
char_spans = [doc.char_span(sent_span.start, sent_span.end, alignment_mode='contract')
for sent_span in sents_char_spans]
start_token_ids = [span[0].idx for span in char_spans if span is not None]
for token in doc:
token.is_sent_start = True if token.idx in start_token_ids else False
return doc

if name == "main":
text = "My name is Jonas E. Smith. Please turn to p.55."
nlp = spacy.blank('en')
doc = nlp(text)
# add as a spacy pipeline
nlp.add_pipe('sbd')
print('sent_id', 'sentence', sep='\t|\t')
for sent_id, sent in enumerate(doc.sents, start=1):
print(sent_id, sent.text, sep='\t|\t')

Facing the same issue