YonatanDavidov/qasem-fr-claire-lora

QASem French LoRA Adapter (Claire 7B)

This repository provides a LoRA adapter for French QA-based semantic parsing (QASem).

Overview

This repository provides a LoRA adapter for performing QA-based semantic parsing (QASem) in French.

QASem represents predicate–argument structure using natural-language question–answer pairs, rather than predefined semantic role labels. This makes the representation more interpretable and flexible across languages.

The adapter is built on top of:

Base model: OpenLLM-France/Claire-7B-FR-Instruct-0.1

and enables efficient semantic parsing using parameter-efficient fine-tuning (LoRA).

✨ Why this model matters

Traditional semantic role labeling methods rely on fixed label schemas and costly expert annotation.

This model takes a different approach by:

• —Representing semantics using natural-language question–answer pairs
• —Enabling automatic dataset construction via cross-lingual projection
• —Supporting scalable semantic parsing across languages
• —Achieving strong performance with efficient fine-tuned models

This makes it possible to build semantic parsers for new languages with minimal cost.

Use Cases

This model can be used for:

• —Research in QA-based semantic parsing (QASem) and semantic representation learning
• —Extraction of predicate–argument structures from French text
• —Automatic dataset creation for training semantic models in new languages
• —Downstream NLP applications such as:
• —Information extraction
• —Text understanding
• —Factuality and attribution evaluation

Language

• —French 🇫🇷

Training Data

The model was trained on the Multilingual QASem Dataset:

👉 https://huggingface.co/datasets/biu-nlp/MultilingualQASemDatasets

The dataset includes:

• —Automatically generated QASem annotations
• —Train / Development / Test splits
• —Multiple languages: French, Hebrew, Russian
• —Tens of thousands of QA pairs per language

The data was constructed using a cross-lingual projection approach, ensuring scalability across languages.

📄 Associated Work

This model and the underlying dataset are introduced in: Effective QA-Driven Annotation of Predicate-Argument Relations Across Languages.

The paper presents the full methodology, dataset construction process, and evaluation across multiple languages.

🚀 Quick Start (Recommended)

Using the XQASem Parser

For a simple and structured interface, you can use the XQASem parser.

Installation

pip install xqasem

Install the spaCy pipeline:

python -m spacy download fr_core_news_md

Basic Example

from xqasem import XQasemParser

parser = XQasemParser.from_language("fr")

sentences = [
    "Les experts ont souligné que le nouvel algorithme accélère considérablement le traitement des requêtes complexes."
]

df = parser(sentences)

print(df)

Output Format

The model produces structured predicate–argument representations in the form of:

• —A predicate (verb or nominal)
• —A natural-language question
• —A corresponding answer span from the sentence

This structure can be easily converted into tabular or JSON format for downstream use.

Example Output

👉 For more details and advanced usage, see the project repository: https://github.com/JohnnieDavidov/xqasem

Manual Model Loading (Advanced)

from transformers import AutoTokenizer
from peft import AutoPeftModelForCausalLM

model_id = "YonatanDavidov/qasem-fr-claire-lora"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoPeftModelForCausalLM.from_pretrained(model_id)

Limitations

• —Performance may degrade on out-of-domain text
• —Complex or ambiguous predicates may lead to inconsistent outputs
• —The model is optimized for QASem-style generation and not for general-purpose text generation

📄 Citation

If you use this model, please cite our work:

@inproceedings{davidov-etal-2026-effective,
    title = "Effective {QA}-Driven Annotation of Predicate{--}Argument Relations Across Languages",
    author = "Davidov, Jonathan  and
      Slobodkin, Aviv  and
      Klein, Shmuel Tomi  and
      Tsarfaty, Reut  and
      Dagan, Ido  and
      Klein, Ayal",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.eacl-long.112/",
    doi = "10.18653/v1/2026.eacl-long.112",
    pages = "2484--2502",
    ISBN = "979-8-89176-380-7",
}