PerkwE_COQA: Enhanced Persian Conversational Question Answering by combining contextual keyword extraction with Large Language Models

TL;DR

This paper introduces a novel Persian conversational question-answering system that enhances LLM capabilities by integrating contextual keyword extraction, resulting in more accurate and contextually relevant responses in complex conversational scenarios.

Contribution

It proposes a new method combining LLMs with keyword extraction to improve Persian CQA performance, especially for implicit and complex questions.

Findings

Achieved up to 8% higher performance than existing methods.

Effectively handles implicit and complex conversational questions.

Significantly improves contextual understanding in Persian CQA.

Abstract

Smart cities need the involvement of their residents to enhance quality of life. Conversational query-answering is an emerging approach for user engagement. There is an increasing demand of an advanced conversational question-answering that goes beyond classic systems. Existing approaches have shown that LLMs offer promising capabilities for CQA, but may struggle to capture the nuances of conversational contexts. The new approach involves understanding the content and engaging in a multi-step conversation with the user to fulfill their needs. This paper presents a novel method to elevate the performance of Persian Conversational question-answering (CQA) systems. It combines the strengths of Large Language Models (LLMs) with contextual keyword extraction. Our method extracts keywords specific to the conversational flow, providing the LLM with additional context to understand the user's intent and generate more relevant and coherent responses. We evaluated the effectiveness of this combined approach through various metrics, demonstrating significant improvements in CQA performance compared to an LLM-only baseline. The proposed method effectively handles implicit questions, delivers contextually relevant answers, and tackles complex questions that rely heavily on conversational context. The findings indicate that our method outperformed the evaluation benchmarks up to 8% higher than existing methods and the LLM-only baseline.