Test Drive: Gemma APS
Published on .
Today I’m test driving Gemma APS “models for text-to-propositions segmentation.” “Abstractive proposition segmentation” (aka claim extraction) is a new concept to me aimed at solving problems including fact-checking. Amazon’s RefChecker is another research here. The idea is break a passage down into simple, individual claims with minimal changes to the text so that they can be processed indepdently. The process is simple:
- Accept the Gemma terms and login to HuggingFace
- Implement :)
The output is a list of claims
I just used the implementation straight from Google
import nltk
import re
nltk.download('punkt')
start_marker = '<s>'
end_marker = '</s>'
separator = '\n'
def create_propositions_input(text: str) -> str:
input_sents = nltk.tokenize.sent_tokenize(text)
propositions_input = ''
for sent in input_sents:
propositions_input += f'{start_marker} ' + sent + f' {end_marker}{separator}'
propositions_input = propositions_input.strip(f'{separator}')
return propositions_input
def process_propositions_output(text):
pattern = re.compile(f'{re.escape(start_marker)}(.*?){re.escape(end_marker)}', re.DOTALL)
output_grouped_strs = re.findall(pattern, text)
predicted_grouped_propositions = []
for grouped_str in output_grouped_strs:
grouped_str = grouped_str.strip(separator)
props = [x[2:] for x in grouped_str.split(separator)]
predicted_grouped_propositions.append(props)
return predicted_grouped_propositions
from transformers import pipeline
import torch
generator = pipeline('text-generation', 'google/gemma-2b-aps-it', device_map='auto', torch_dtype=torch.bfloat16)
passage = 'Sarah Stage, 30, welcomed James Hunter into the world on Tuesday.\nThe baby boy weighed eight pounds seven ounces and was 22 inches long.'
messages = [{'role': 'user', 'content': create_propositions_input(passage)}]
output = generator(messages, max_new_tokens=4096, return_full_text=False)
result = process_propositions_output(output[0]['generated_text'])
print(result)
passage = 'Dante de Blasio, 17, to make his decision by the end of the month. His father has said that despite his six-figure salary the family will struggle to meet cost to send son to Ivy League school.'
messages = [{'role': 'user', 'content': create_propositions_input(passage)}]
output = generator(messages, max_new_tokens=4096, return_full_text=False)
result = process_propositions_output(output[0]['generated_text'])
print(result)Code language: Python (python)