首页|Intent Understanding for Automatic Question Answering in Network Technology Communities Based on Multi-task Learning

Intent Understanding for Automatic Question Answering in Network Technology Communities Based on Multi-task Learning

扫码查看
原文链接
  • NETL
In the realm of automatic question-answering (Q&A) for technical communities， accurately perceiving and predicting user intent is a crucial step towards improving Q&A system performance by integrating user intention with answer reasoning processes。 We conducted research into intent understanding at the sentence level， aiming to clarify the function of each sentence in technical Q&A communities and improve the system's response accuracy。 To address the shortcomings of existing research， which typically ignores information such as speaker type and sentence position， we propose a multi-task learning framework to effectively utilize this information for sentence representation learning。 By doing so， the model can acquire richer interactive question-answer language features， thereby enhancing the performance of intent label classification。 Within this framework， we present two models: BA-multi and CCR-multi。 Our validation experiments on the MSDialog-Intent dataset demonstrate that the multi-task learning model significantly outperforms both the baseline and feature extension models， achieving state-of-the-art performance。

Deep LearningNatural Language ProcessingMulti-task LearningIntent Understanding

Xin Huang、Huilin Song、Mingming Lu

展开 >

School of Software, Jiangxi Normal University, Nanchang 330031, China,Jiangxi Provincial Engineering Research Center of Blockchain Data Security and Governance, Nanchang 330031, China

School of International Economics and Trade, Jiangxi University of Finance and Economics, Nanchang 330013, China,Jiangxi Provincial Engineering Research Center of Blockchain Data Security and Governance, Nanchang 330031, China

School of Electronic Information Engineering, Tongji University, Shanghai 201804, China,Jiangxi Provincial Engineering Research Center of Blockchain Data Security and Governance, Nanchang 330031, China

International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems

Shanghai(CN)

Advances and Trends in Artificial Intelligence. Theory and Applications

117-129

2023

10.1007/978-3-031-36822-6_10