Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning
Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning
复制标题
DOI：
10.1609/aaai.v37i13.26861
复制
发表时间：
2023-06
影响因子：
--
通讯作者：
Joonyoung Kim;Kangwook Lee;Haebin Shin;Hurnjoo Lee;Sechun Kang;Byunguk Choi;Dong Shin;Joohyung Lee
中科院分区：
文献类型：
--
作者：
Joonyoung Kim;Kangwook Lee;Haebin Shin;Hurnjoo Lee;Sechun Kang;Byunguk Choi;Dong Shin;Joohyung Lee
智能手机上添加的新功能越多，用户就越难找到它们。这是因为功能名称通常很短，而且对于用户来说太多了，无法记住确切的单词。用户更愿意询问描述他们正在寻找的特征的上下文查询，但标准的基于词频的搜索无法处理它们。本文提出了一种新颖的检索系统，移动的功能，接受直观和上下文的搜索查询。我们通过对比学习从预先训练的语言模型中训练相关性模型，以感知查询嵌入和索引移动的特征之间的上下文相关性。此外，为了使其使用最少的资源在设备上有效地运行，我们应用知识蒸馏来压缩模型，而不会降低性能。为了验证我们的方法的可行性，我们收集了测试查询，并与当前部署的搜索基线进行了比较实验。结果表明，我们的系统优于其他上下文语句查询，甚至在通常的基于关键字的查询。
The more new features that are being added to smartphones, the harder it becomes for users to find them. This is because the feature names are usually short and there are just too many of them for the users to remember the exact words. The users are more comfortable asking contextual queries that describe the features they are looking for, but the standard term frequency-based search cannot process them. This paper presents a novel retrieval system for mobile features that accepts intuitive and contextual search queries. We trained a relevance model via contrastive learning from a pre-trained language model to perceive the contextual relevance between a query embedding and indexed mobile features. Also, to make it efficiently run on-device using minimal resources, we applied knowledge distillation to compress the model without degrading much performance. To verify the feasibility of our method, we collected test queries and conducted comparative experiments with the currently deployed search baselines. The results show that our system outperforms the others on contextual sentence queries and even on usual keyword-based queries.