Removed old files and added MSRParaphrase parser

This commit is contained in:
Henry Dowd
2025-11-18 19:44:39 +00:00
parent 6bae7a2168
commit 42deee19f6
11 changed files with 96 additions and 77 deletions

View File

@@ -0,0 +1,6 @@
import pandas as pd
def load_msr_data(file_path):
"""Load the MSR Paraphrase Corpus from a TSV file."""
df = pd.read_csv("../data/processed/msr_paraphrase_train.txt", sep='\t', quoting=3)
return df