SynTran-fa: Generating Comprehensive Answers for Farsi QA Pairs via Syntactic Transformation
Preprint
- 22 October 2024
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Generating coherent and comprehensive responses remains a significant challenge Question-Answering (QA) systems when working with short answers especially for low-resourced languages like Farsi. We present a novel approach to expand these answers into complete, fluent responses, addressing the critical issue of limited Farsi resources and models. Our methodology employs a two-stage process: first, we develop a dataset using rule-based techniques on Farsi text, followed by a BERT-based ranking system to ensure fluency and comprehensibility. The resulting model demonstrates strong compatibility with existing QA systems, particularly those based on knowledge graphs. Notably, our system exhibits enhanced performance when integrated with large language models using Chain-of-Thought (CoT) prompting, leveraging detailed explanations rather than single-word answers. Our approach significantly improves response quality and coherence compared to baseline systems. We release our dataset to support further research in Farsi QA\footnote[1]{\href{https://huggingface.co/datasets/SLPL/syntran-fa}{https://huggingface.co/datasets/SLPL/syntran-fa}}.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- HybridFlow: A Flexible and Efficient RLHF Framework2025
- PQuAD: A Persian question answering datasetComputer Speech & Language, 2023
- ParsBERT: Transformer-based Model for Persian Language UnderstandingNeural Processing Letters, 2021
- QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering2021
- Stanza: A Python Natural Language Processing Toolkit for Many Human Languages2020
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019
- BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions2019
- TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension2017
- SQuAD: 100,000+ Questions for Machine Comprehension of Text2016