README.md

---
library_name: transformers
base_model:
- google-t5/t5-base
---

# Model Card for STEP

<!-- Provide a quick summary of what the model is/does. -->
This model is pre-trained to perform (random) syntactic transformations of English sentences. The prefix given to the model decides which syntactic transformation to apply. 

See [Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations](https://arxiv.org/abs/2407.04543) for full details.

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

- **Developed by:** Matthias Lindemann
- **Funded by [optional]:** UKRI, Huawei, Dutch National Science Foundation
- **Model type:** Sequence-to-Sequence model
- **Language(s) (NLP):** English
- **License:** [More Information Needed]
- **Finetuned from model:** T5-Base

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/namednil/step
- **Paper:** [Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations](https://arxiv.org/abs/2407.04543)

## Uses

Syntax-sensitive sequence-to-sequence for English such as passivization, semantic parsing, chunking, question formation, ...
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

This model needs to be fine-tuned as it implements random syntactic transformations.

## Bias, Risks, and Limitations

The model was exposed to the C4 corpus (pre-training data of T5) and is based on T5 and hence likely inherits biases from that.
<!-- This section is meant to convey both technical and sociotechnical limitations. -->

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.


## Model Examination [optional]

We identified the following interpretable transformation look-up heads (see paper for details) for UD relations (in the format (layer, head) both with 0-based indexing):

```python
{'cop': [(0, 3), (4, 11), (7, 11), (8, 11), (9, 5), (9, 6), (10, 5), (11, 11)],
 'expl': [(0, 7), (7, 11), (8, 2), (8, 11), (9, 6), (9, 7), (11, 11)],
 'amod': [(4, 6), (6, 6), (7, 11), (8, 0), (8, 11), (9, 5), (11, 11)],
 'compound': [(4, 6), (6, 6), (7, 6), (7, 11), (8, 11), (9, 5), (9, 7), (9, 11), (11, 11)],
 'det': [(4, 6), (7, 11), (8, 11), (9, 5), (9, 6), (10, 5)],
 'nmod:poss': [(4, 6), (4, 11), (7, 11), (8, 11), (9, 5), (9, 6), (11, 11)],
 'advmod': [(4, 11), (6, 6), (7, 11), (8, 11), (9, 5), (9, 6), (9, 11), (11, 11)],
 'aux': [(4, 11), (7, 11), (8, 11), (9, 5), (9, 6), (10, 5), (11, 11)],
 'mark': [(4, 11), (8, 11), (9, 5), (9, 6), (11, 11)],
 'fixed': [(5, 5), (8, 2), (8, 6), (9, 4), (9, 6), (10, 1), (10, 4), (10, 6), (10, 11), (11, 11)],
 'compound:prt': [(6, 2), (6, 6), (7, 11), (8, 2), (8, 6), (9, 4), (9, 6), (10, 4), (10, 6),
                  (10, 11), (11, 11)],
 'acl': [(6, 6), (7, 11), (8, 2), (9, 4), (10, 6), (10, 11), (11, 11)],
 'nummod': [(6, 6), (7, 11), (8, 11), (9, 6), (11, 11)],
 'flat': [(6, 11), (7, 11), (8, 2), (8, 11), (9, 4), (10, 6), (10, 11), (11, 11)],
 'aux:pass': [(7, 11), (8, 11), (9, 5), (9, 6), (10, 5), (11, 11)],
 'iobj': [(7, 11), (10, 4), (10, 11)],
 'nsubj': [(7, 11), (8, 11), (9, 5), (9, 6), (9, 11), (11, 11)],
 'obj': [(7, 11), (10, 4), (10, 6), (10, 11), (11, 11)],
 'obl:tmod': [(7, 11), (9, 4), (10, 4), (10, 6), (11, 11)], 'case': [(8, 11), (9, 5)],
 'cc': [(8, 11), (9, 5), (9, 6), (11, 11)],
 'obl:npmod': [(8, 11), (9, 6), (9, 11), (10, 6), (11, 11)],
 'punct': [(8, 11), (9, 6), (10, 6), (10, 11), (11, 5)], 'csubj': [(9, 11), (10, 6), (11, 11)],
 'nsubj:pass': [(9, 11), (10, 6), (11, 11)], 'obl': [(9, 11), (10, 6)], 'acl:relcl': [(10, 6)],
 'advcl': [(10, 6), (11, 11)], 'appos': [(10, 6), (10, 11), (11, 11)], 'ccomp': [(10, 6)],
 'conj': [(10, 6)], 'nmod': [(10, 6), (10, 11)], 'vocative': [(10, 6)],
 'xcomp': [(10, 6), (10, 11)]}
```
                

## Environmental Impact

- **Hardware Type:** Nvidia 2080 TI
- **Hours used:** 30
- **Compute Regsion**: Scotland
- **Carbon Emitted**: 0.2 kg CO2eq

## Technical Specifications

### Model Architecture and Objective

T5-Base, 12 layers, hidden dimensionality of 768.

## Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**
```
@inproceedings{lindemann-etal-2024-strengthening,
    title = "Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations",
    author = "Lindemann, Matthias  and
      Koller, Alexander  and
      Titov, Ivan",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.645/",
    doi = "10.18653/v1/2024.emnlp-main.645",
}
```