juliaromberg/distilbert-base-german-cased_cimt-argument

Model Description

distilbert-base-german-cased_cimt-argument is a fine-tuned DistilBERT model that is built to predict whether a sentence contains an argument. It has been trained to recognize two classes: argumentative (LABEL_1) and non-argumentative (LABEL_0).

Specifically, this model is a distilbert-base-german-cased that was fine-tuned on https://github.com/juliaromberg/cimt-argument-mining-dataset.

Background

This work is based on research in the project CIMT, which investigates the chances and challenges of involving citizens in political decisions in the context of sustainable mobility transitions. (for more information, visit https://www.cimt-hhu.de/en/)

Details & Evaluation Results

This model is a distilled version of the BERT model that is described in detail in the publication https://aclanthology.org/2021.argmining-1.9/. The distilled model halves the size of the model while maintaining a similar macro F_1 performance.

Usage

from transformers import AutoModelForSequenceClassification, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("juliaromberg/distilbert-base-german-cased_cimt-argument")
model = AutoModelForSequenceClassification.from_pretrained("juliaromberg/distilbert-base-german-cased_cimt-argument", use_safetensors=True)

Citation

@inproceedings{romberg-conrad-2021-citizen,
    title = "Citizen Involvement in Urban Planning - How Can Municipalities Be Supported in Evaluating Public Participation Processes for Mobility Transitions?",
    author = "Romberg, Julia  and
      Conrad, Stefan",
    editor = "Al-Khatib, Khalid  and
      Hou, Yufang  and
      Stede, Manfred",
    booktitle = "Proceedings of the 8th Workshop on Argument Mining",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.argmining-1.9",
    doi = "10.18653/v1/2021.argmining-1.9",
    pages = "89--99",
    abstract = "Public participation processes allow citizens to engage in municipal decision-making processes by expressing their opinions on specific issues. Municipalities often only have limited resources to analyze a possibly large amount of textual contributions that need to be evaluated in a timely and detailed manner. Automated support for the evaluation is therefore essential, e.g. to analyze arguments. In this paper, we address (A) the identification of argumentative discourse units and (B) their classification as major position or premise in German public participation processes. The objective of our work is to make argument mining viable for use in municipalities. We compare different argument mining approaches and develop a generic model that can successfully detect argument structures in different datasets of mobility-related urban planning. We introduce a new data corpus comprising five public participation processes. In our evaluation, we achieve high macro F1 scores (0.76 - 0.80 for the identification of argumentative units; 0.86 - 0.93 for their classification) on all datasets. Additionally, we improve previous results for the classification of argumentative units on a similar German online participation dataset.",
}