qwen3-4b-bkee-argument-assigner

Qwen3-4B BKEE Argument Assigner

A Vietnamese event argument role assignment model fine-tuned from unsloth/Qwen3-4B-Instruct-2507. Given a sentence, an event trigger, and a set of candidate entities, the model links each relevant entity to its semantic role (one of BKEE's 28 argument roles) under that trigger, along with a step-by-step natural-language reasoning trace.

This is one of four task-specific checkpoints from a distant-supervision Vietnamese event-extraction pipeline, alongside:

• hadeseus/qwen3-4b-bkee-entity-extraction
• hadeseus/qwen3-4b-bkee-event-extraction
• hadeseus/qwen3-4b-bkee-full-extraction

Training Data

The model was trained on a silver-labeled reasoning dataset derived from BKEE (a Vietnamese Event Extraction dataset introduced at LREC-COLING 2024, containing 1,066 manually annotated documents across 33+ event types and 28 argument roles).

The silver data was produced via a distant supervision pipeline:

1. BKEE gold entity, trigger, and argument-role labels are used to prompt an LLM to generate step-by-step Chain-of-Thought reasoning explaining why an entity fills a given semantic role under a trigger.
2. Predictions are validated against Pydantic schemas and checked against BKEE gold annotations (non-empty gold labels are strictly matched; sentences with empty gold labels allow the LLM to surface additional plausible role assignments).
3. Verified reasoning traces are combined with the original BKEE sentences to form the supervised fine-tuning dataset for this checkpoint.

Note: this model is trained on machine-generated (silver) reasoning data aligned to BKEE's gold argument labels, not on human-written explanations.

Intended Use

Given a Vietnamese sentence, an identified event trigger, and candidate entities, the model outputs a reasoning trace followed by the argument role assigned to each relevant entity. It is intended as the argument-linking stage of a larger event extraction pipeline (see the full-extraction checkpoint for an end-to-end variant).

Usage

System prompt:

Gán nhãn loại tham số sự kiện cho các thực thể phù hợp từ danh sách thực thể ứng viên đã cho. Hãy suy nghĩ theo từng bước.

User prompt (structured template):

- Văn bản: "{sentence}"
- Loại sự kiện: "{event_type}"
- Trigger sự kiện: "{event_trigger}"
- Danh sách thực thể ứng viên: "{entities}"
- Danh sách loại tham số sự kiện:
{arguments_hint}

Output: reasoning followed by {"arguments": [{"text": ..., "type": ...}]}.

Citation

If you use this model, please cite the underlying BKEE dataset:

@inproceedings{nguyen-etal-2024-bkee,
    title = "{BKEE}: Pioneering Event Extraction in the {V}ietnamese Language",
    author = "Nguyen, Thi-Nhung  and
      Tran, Bang Tien  and
      Luu, Trong-Nghia  and
      Nguyen, Thien Huu  and
      Nguyen, Kiem-Hieu",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.217",
    pages = "2421--2427"
}