Metadata-Version: 2.1
Name: minicons
Version: 0.2.2
Summary: A package of useful functions to analyze transformer based language models.
Home-page: https://github.com/kanishkamisra/minicons
License: MIT
Keywords: transformers,language models,nlp,interpretability
Author: Kanishka Misra
Author-email: kmisra@purdue.edu
Requires-Python: >=3.7.1,<4
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Requires-Dist: pandas (>=1.3.5,<2.0.0)
Requires-Dist: polyleven (>=0.7,<0.8)
Requires-Dist: torch (>=1.8.0,<2.0.0)
Requires-Dist: transformers (>=4.4.1,<5.0.0)
Requires-Dist: urllib3 (>=1.26.7,<2.0.0)
Project-URL: Repository, https://github.com/kanishkamisra/minicons
Description-Content-Type: text/markdown

# minicons

[![Downloads](https://static.pepy.tech/personalized-badge/minicons?period=total&units=international_system&left_color=black&right_color=brightgreen&left_text=Downloads)](https://pepy.tech/project/minicons)

Helper functions for analyzing Transformer based representations of language

This repo is a wrapper around the `transformers` [library](https://huggingface.co/transformers) from hugging face :hugs:


## Installation

Install from Pypi using:

```pip install minicons```

## Supported Functionality

- Extract word representations from Contextualized Word Embeddings
- Score sequences using language model scoring techniques, including masked language models following [Salazar et al. (2020)](https://www.aclweb.org/anthology/2020.acl-main.240.pdf).


## Examples

1. Extract word representations from contextualized word embeddings:

```py
from minicons import cwe

model = cwe.CWE('bert-base-uncased')

context_words = [("I went to the bank to withdraw money.", "bank"), 
                 ("i was at the bank of the river ganga!", "bank")]

print(model.extract_representation(context_words, layer = 12))

''' 
tensor([[ 0.5399, -0.2461, -0.0968,  ..., -0.4670, -0.5312, -0.0549],
        [-0.8258, -0.4308,  0.2744,  ..., -0.5987, -0.6984,  0.2087]],
       grad_fn=<MeanBackward1>)
'''
```

2. Compute sentence acceptability measures (surprisals) using Word Prediction Models:

```py
from minicons import scorer

mlm_model = scorer.MaskedLMScorer('bert-base-uncased', 'cpu')
ilm_model = scorer.IncrementalLMScorer('distilgpt2', 'cpu')

stimuli = ["The keys to the cabinet are on the table.",
           "The keys to the cabinet is on the table."]

# use sequence_score with different reduction options: 
# Sequence Surprisal - lambda x: -x.sum(1)
# Sequence Log-probability - lambda x: x.sum(1)
# Sequence Surprisal, normalized by number of tokens - lambda x: -x.mean(1)
# Sequence Log-probability, normalized by number of tokens - lambda x: x.mean(1)
# and so on...

print(ilm_model.sequence_score(stimuli, reduction = lambda x: -x.sum(0).item()))

'''
[39.879737854003906, 42.75846481323242]
'''

# MLM scoring, inspired by Salazar et al., 2020
print(mlm_model.sequence_score(stimuli, reduction = lambda x: -x.sum(0).item()))
'''
[13.962685585021973, 23.415111541748047]
'''
```

## Tutorials

- [Introduction to using LM-scoring methods using minicons](https://kanishka.xyz/post/minicons-running-large-scale-behavioral-analyses-on-transformer-lms/)
- [Computing sentence and token surprisals using minicons](examples/surprisals.md)
- [Extracting word/phrase representations using minicons](examples/word_representations.md)

## Recent Updates
- **November 6, 2021:** MLM scoring has been fixed! You can now use `model.token_score()` and `model.sequence_score()` with `MaskedLMScorers` as well!
