license: apache-2.0
language:
- de
pipeline_tag: text-generation
tags:
- german
- deutsch
- simplification
- vereinfachung
Model Card for Model ID
This model was used in our experiments in our paper: Elaborative Simplification for German-Language Texts. We have uploaded this model for transparency and replicability of our experiments. If however you are interested in German text simplification in general, we recommend our more recent model.
We fine-tuned meta-llama/Meta-Llama-3-8B-Instruct with a set of ca. 2000 newspaper articles which have been simplified by the Austrian Press Agency. This model was trained with the standard and the B1 level texts.
Model Details
Model Description
- Developed by: Freya Hewett, Hadi Asghari
- Model type: simplification model, text generation
- Language(s) (NLP): German
- License: Apache 2.0
- Finetuned from model: meta-llama/Meta-Llama-3-8B-Instruct
Model Sources
- Repository: GermanElabSimplification
- Paper: Elaborative Simplification for German-Language Texts
Uses
Direct Use
This model works best for simplifying German-language newspaper articles (news items, not commentaries or editorials). It may work for other types of texts.
Downstream Use
We have fine-tuned using only newspaper articles. We have not yet performed extensive out-of-domain testing, but believe that the model's capabilities could be improved by fine-tuning on more diverse data.
Bias, Risks, and Limitations
As with most text generation models, the model sometimes produces information that is incorrect.
Recommendations
Please check manually that your output text corresponds to the input text, as factual inconsistencies may have arisen.
How to Get Started with the Model
To load the model using transformers:
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
device = "cuda"
tokenizer = AutoTokenizer.from_pretrained("frhew/sigdial_ft_b1")
model = AutoModelForCausalLM.from_pretrained("frhew/sigdial_ft_b1", torch_dtype=torch.float16).to(device)
We used the following prompt at inference to test our model:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Du bist ein hilfreicher Assistent und hilfst dem User, Texte besser zu verstehen.<|eot_id|><|start_header_id|>user<|end_header_id|>
Kannst du bitte den folgenden Text zusammenfassen und sprachlich auf ein B1-Niveau in Deutsch vereinfachen? Schreibe maximal 5 Sätze.
{input_text}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Training Details
Training Data
A sample of the data used to train our model can be found here.
Training Hyperparameters
Evaluation
The right hand side shows the results of the manual evaluation, done on the outputs from each model for 35 texts. M.P. stands for meaning preservation, S for simplification, C for coherence, F for factuality; the score represents the percentage of yes answers. More details on the evaluation can be found in the paper. For all metrics, higher is better.
| Model | Prompt | Test set | SARI | FRE | M.P. | S | C | F | Avg. |
|---|---|---|---|---|---|---|---|---|---|
| Baseline | Basic | A2 | 41.2 | 59.4 | .89 | .38 | .96 | .84 | .77 |
| FT-A2 | Basic | A2 | 44.0 | 70.6 | .49 | .82 | .56 | .64 | .63 |
| Baseline | Basic | B1 | 42.3 | 56.8 | .85 | .4 | .9 | .9 | .76 |
| FT-B1 | Basic | B1 | 42.4 | 60.0 | .75 | .55 | .6 | .75 | .66 |
Summary
Citation
BibTeX:
@inproceedings{hewett-etal-2024-elaborative, title = "Elaborative Simplification for {G}erman-Language Texts", author = "Hewett, Freya and Asghari, Hadi and Stede, Manfred", editor = "Kawahara, Tatsuya and Demberg, Vera and Ultes, Stefan and Inoue, Koji and Mehri, Shikib and Howcroft, David and Komatani, Kazunori", booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue", month = sep, year = "2024", address = "Kyoto, Japan", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.sigdial-1.3", doi = "10.18653/v1/2024.sigdial-1.3", pages = "29--39"}
APA:
Freya Hewett, Hadi Asghari, and Manfred Stede. 2024. Elaborative Simplification for German-Language Texts. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 29–39, Kyoto, Japan. Association for Computational Linguistics.
Model Card Contact
frhew