---
language:
- en
---

# O->LED_para document simplification system

This is a pretrained version of the document simplification model presented in the Findings of ACL 2023 paper ["Context-Aware Document Simplification"](https://arxiv.org/abs/2305.06274). 

It is a system based on the [Longformer encoder-decoder](https://huggingface.co/allenai/led-base-16384) that operates at the paragraph-level and is intended to be guided by a planner.

Target reading levels (1-4) should be indicated via a control token prepended to each input sequence ("\<RL_1\>", "\<RL_2\>", "\<RL_3\>", "\<RL_4\>"). If using the terminal interface, this will be handled automatically.

## How to use
It is recommended to use the [plan_simp](https://github.com/liamcripwell/plan_simp/tree/main) library to interface with the model.

Here is how to load this model in PyTorch:

```python
# loading
from plan_simp.models.bart import load_simplifier
simplifier, tokenizer, hparams = load_simplifier("liamcripwell/o-ledpara")

# generation
from plan_simp.scripts.generate import Launcher
launcher = Launcher()
launcher.dynamic(model_ckpt="liamcripwell/o-ledpara", clf_model_ckpt="liamcripwell/pgdyn-plan", **params)
```

Plan-guided generation and evaluation can be run from the terminal (see the repo for more details).

```bash
python doc_simp/scripts/generate.py dynamic
  --clf_model_ckpt=liamcripwell/pgdyn-plan
  --model_ckpt=liamcripwell/o-ledpara
  --test_file=<test_data>
  --doc_id_col=pair_id
  --context_dir=<context_dir>
  --out_file=<output_csv>
  --reading_lvl=s_level
  --context_doc_id=pair_id
  --para_lvl=True

python plan_simp/scripts/eval_simp.py
    --input_data=newselaauto_docs_test.csv
    --output_data=test_out_oledpara.csv
    --x_col=complex_str
    --r_col=simple_str
    --y_col=pred
    --doc_id_col=pair_id
    --prepro=True
    --sent_level=True
```