def calculate_bleu_for_pdf(reference_pdf, candidate_text): ref_clean = clean_pdf_text(reference_pdf) ref_sents = chunk_sentences(ref_clean) cand_sents = chunk_sentences(candidate_text)
import pdfplumber from nltk.translate.bleu_score import sentence_bleu, SmoothingFunction import re def clean_pdf_text(pdf_path): with pdfplumber.open(pdf_path) as pdf: full_text = "" for page in pdf.pages: text = page.extract_text() # Fix line-break hyphens text = re.sub(r'(\w+)-\n(\w+)', r'\1\2', text) # Replace newlines with spaces text = re.sub(r'\n+', ' ', text) full_text += text + " " return full_text.strip() bleu+pdf+work
Introduction In the rapidly evolving world of machine translation (MT) and localization, three terms increasingly intersect in the daily workflow of linguists, developers, and project managers: BLEU , PDF , and Work . and project managers: BLEU