动态管理对话上下文，提升智能问答系统准确率
Towards Adaptive Context Management for Intelligent Conversational Question Answering
- 通过动态调整上下文长度，保留最相关最近信息
- 滑动窗口摘要旧对话，超限则提取关键实体
- 适合需要长对话记忆的智能客服与问答系统
本文提出一种自适应上下文管理（ACM）框架，用于对话式问答系统（ConvQA）。该框架通过上下文管理模块（CM）、摘要模块（SM）和实体抽取模块（EE），动态优化对话历史的使用。CM模块根据模型的令牌限制动态调整上下文大小，确保关键信息不丢失；SM模块对旧对话内容进行滑动窗口摘要；当摘要窗口超限时，EE模块提取并保留最早对话轮次中的关键实体。实验表明，该框架能生成更准确且上下文相关的回答，显著提升ConvQA系统的鲁棒性与可扩展性。
原文摘要 · Abstract (English)
This particular paper introduces an Adaptive Context Management (ACM) framework for the Conversational Question Answering (ConvQA) systems. The key objective of the ACM framework is to optimize the use of the conversation history by dynamically managing context for maximizing the relevant information provided to a ConvQA model within its token limit. Our approach incorporates a Context Manager (CM) Module, a Summarization (SM) Module, and an Entity Extraction (EE) Module in a bid to handle the conversation history efficaciously. The CM Module dynamically adjusts the context size, thereby preserving the most relevant and recent information within a model's token limit. The SM Module summarizes the older parts of the conversation history via a sliding window. When the summarization window exceeds its limit, the EE Module identifies and retains key entities from the oldest conversation turns. Experimental results demonstrate the effectiveness of our envisaged framework in generating accurate and contextually appropriate responses, thereby highlighting the potential of the ACM framework to enhance the robustness and scalability of the ConvQA systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。