基于交叉注意力多源数据增强的情境感知查询建议方法

doi:10.13209/j.0479-8023.2023.074

北京大学学报自然科学版 ›› 2024, Vol. 60 ›› Issue (1): 34-42.DOI: 10.13209/j.0479-8023.2023.074

基于交叉注意力多源数据增强的情境感知查询建议方法

张乃洲^†, 曹薇

河南财经政法大学计算机与信息工程学院, 郑州 450046

收稿日期:2023-05-15 修回日期:2023-07-31 出版日期:2024-01-20 发布日期:2024-01-20
通讯作者: 张乃洲, E-mail: zhangnz(at)126.com
基金资助:
国家自然科学基金(62072156)资助

A Context-Aware Query Suggestion Method Based on Multi-source Data Augmentation through Cross-Attention

ZHANG Naizhou^†, CAO Wei

College of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou 450046

Received:2023-05-15 Revised:2023-07-31 Online:2024-01-20 Published:2024-01-20
Contact: ZHANG Naizhou, E-mail: zhangnz(at)126.com

摘要/Abstract

摘要：

当前基于神经网络模型的查询建议研究往往单独采用查询日志会话中的查询序列作为训练数据, 但由于查询本身缺乏句法关系, 甚至缺失语义, 导致神经网络模型不能充分挖掘和推理查询序列中各种词或概念之间语义关系。针对这一问题, 提出一种基于交叉注意力多源数据增强(MDACA)的Transformer模型框架, 用于生成情境感知的查询建议。采用基于Transformer的编码器-解码器模型, 利用交叉注意力机制, 融合了查询层、文档语义层以及全局查询建议信息。实验结果表明, 与目前方法相比, 该方法能生成具有更高相关性的情境感知查询建议。

关键词: 查询建议, 数据增强, 交叉注意力, 情境感知, Transformer模型

Abstract:

Most existing neural network-based approaches for query suggestion use solely query sequences in query logs as training data. However, these methods cannot fully mine and infer all kinds of semantic relationships among words or concepts from query sequences because queries in query sequences inherently suffer from a lack of syntactic relation, even a loss of semantics. To solve this problem, this paper proposes a new neural network model based on multi-source data augmentation through cross-attention (MDACA) for generating context-aware query suggestions. Proposed model adopts a Transformer-based encoder-decoder model that incorporates document-level semantics and global query suggestions into query-level information through cross-attention. The experimental results show that in contrast to the current suggestion models, the proposed model can generate context-aware query suggestions with higher relevance.

Key words: query suggestion, data augmentation, cross-attention, context-aware, Transformer model

张乃洲, 曹薇. 基于交叉注意力多源数据增强的情境感知查询建议方法[J]. 北京大学学报自然科学版, 2024, 60(1): 34-42.

ZHANG Naizhou, CAO Wei. A Context-Aware Query Suggestion Method Based on Multi-source Data Augmentation through Cross-Attention[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2024, 60(1): 34-42.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://xbna.pku.edu.cn/CN/10.13209/j.0479-8023.2023.074

https://xbna.pku.edu.cn/CN/Y2024/V60/I1/34

[1]	丁家杰, 肖康, 叶恒, 周夏冰, 张民. 面向问答领域的数据增强方法[J]. 北京大学学报自然科学版, 2022, 58(1): 54-60.
[2]	王雅松, 刘明童, 张玉洁, 徐金安, 陈钰枫. 复述平行语料构建及其应用方法研究[J]. 北京大学学报自然科学版, 2021, 57(1): 68-74.
[3]	段建勇, 袁阳, 王昊. 基于Transformer局部信息及语法增强架构的中文拼写纠错方法[J]. 北京大学学报自然科学版, 2021, 57(1): 61-67.
[4]	朱钦佩, 缪庆亮. 开放域对话系统的抗噪回复生成模型[J]. 北京大学学报自然科学版, 2021, 57(1): 38-44.

基于交叉注意力多源数据增强的情境感知查询建议方法

A Context-Aware Query Suggestion Method Based on Multi-source Data Augmentation through Cross-Attention

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

留言