henry/paraphrase_detector
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

moved file

Browse Source
This commit is contained in:
Henry Dowd
2025-11-14 11:52:32 +00:00
parent 188a8e5852
commit 00fd620544
2 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@@ -1,2 +1,3 @@
venv venv
.vscode .vscode
.idea

7
testing/dataset_testing.py → dataset_testing.py
View File

@@ -1,9 +1,10 @@
import spacy import spacy
from datasets import load_dataset
from tools import parser from tools import parser
# Load spaCy and dataset # Load spaCy and dataset
nlp = spacy.load("en_core_web_sm") nlp = spacy.load("en_core_web_sm")
dataset = parser.load_dataset("glue", "mrpc") dataset = load_dataset("glue", "mrpc")
def process_sentence_pair(sentence1, sentence2): def process_sentence_pair(sentence1, sentence2):
"""Parse both sentences and extract their dependency structures""" """Parse both sentences and extract their dependency structures"""
@@ -27,7 +28,7 @@ def process_sentence_pair(sentence1, sentence2):
# Process a few examples from the dataset # Process a few examples from the dataset
print("Processing MRPC examples...") print("Processing MRPC examples...")
for i in range(3): # Just do first 3 examples for i in range(5): # Just do first 5 examples
example = dataset['train'][i] example = dataset['train'][i]
result = process_sentence_pair(example['sentence1'], example['sentence2']) result = process_sentence_pair(example['sentence1'], example['sentence2'])
@@ -37,5 +38,5 @@ for i in range(3): # Just do first 3 examples
print(f"Label: {example['label']} (1=paraphrase, 0=not paraphrase)") print(f"Label: {example['label']} (1=paraphrase, 0=not paraphrase)")
print(f"\nDependencies for Sentence 1:") print(f"\nDependencies for Sentence 1:")
for dep in result['dependencies1'][:5]: # Show first 5 dependencies for dep in result['dependencies1'][:55]: # Show first 55 dependencies (Likely All)
print(f" {dep['word']} --{dep['dep_type']}--> {dep['head']}") print(f" {dep['word']} --{dep['dep_type']}--> {dep['head']}")