计算机技术与发展2024，Vol.34Issue(1)：121-127,7.DOI:10.3969/j.issn.1673-629X.2024.01.018
两阶段文档筛选和异步多粒度图多跳问答
Two-stage Document Filtering and Asynchronous Multi-granularity Graph Multi-hop Question Answering
摘要
Abstract
Multi-hop question answering aims to predict the answer to a question and the supporting facts for the answer by reasoning over the content of multiple documents.However,current multi-hop question answering methods aim to find all documents related to the question in the document filtering task,without considering whether all these documents are useful for finding the answer.Therefore,we propose a two-stage document filtering approach.In the first stage,the documents are scored and a small threshold is set to obtain as many relevant documents as possible to ensure a high recall of documents.In the second stage,the inference path of the question answer is modeled,and the documents are extracted again based on the first stage to ensure high accuracy.In addition,we propose a novel asyn-chronous update mechanism for answer prediction and supporting fact prediction for multi-granularity graph composed of documents.The proposed asynchronous update mechanism divides the multi-grain graph into heterogeneous and homogeneous graphs to perform a-synchronous updates for better multi-hop inference.The performance of the proposed method is better than that of the current mainstream multi hop question answering method,and the effectiveness of the proposed method is verified.关键词
多跳问答/文档筛选/多粒度图/异步更新/答案预测Key words
multi-hop question answering/document filtering/multi-granularity graph/asynchronous update/answer prediction分类
信息技术与安全科学引用本文复制引用
张雪松,李冠君,聂士佳,张大伟,吕钊,陶建华..两阶段文档筛选和异步多粒度图多跳问答[J].计算机技术与发展,2024,34(1):121-127,7.基金项目
国家重点研发计划(2020AAA0140003) （2020AAA0140003）
浙江实验室开放研究项目(2021KH0AB06) （2021KH0AB06）
北京市科委、中关村管委会计划(Z211100004821013) （Z211100004821013）
