arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2309.01606cs.CL
收藏

Geo-Encoder:一种面向中文地理重排序的块-论元双编码器框架

Geo-Encoder: A Chunk-Argument Bi-Encoder Framework for Chinese Geographic Re-Ranking

Huazhong University of Science and Technology(华中科技大学);Alibaba Group(阿里巴巴集团);School of Computer Science and Engineering, South China University of Technology(华南理工大学计算机科学与工程学院);University of Copenhagen(哥本哈根大学)

Yong Cao, Ruixue Ding, Boli Chen, Xianzhi Li, Min Chen, Daniel Hershcovich, Pengjun Xie, Fei Huang

AI总结:

针对中文地理重排序任务,提出Geo-Encoder双编码器框架,通过地理分块、多任务学习与异步更新机制融入地理语义,在两个数据集上超越现有最优基线,显著提升MGEO-BERT的Hit@1指标。

摘要:

中文地理重排序任务旨在从检索到的候选地址中找出最相关的地址,这对导航地图等位置相关服务至关重要。与通用语句不同,地理上下文与地理概念紧密交织,涵盖从通用跨度(如省份)到特定跨度(如道路)的各类地理单元。针对这一特性,我们提出了名为Geo-Encoder的创新框架,以更有效地将中文地理语义融入重排序流程。我们的方法首先利用现成工具将文本与地理跨度关联,将其作为分块单元。随后,我们提出多任务学习模块,同时获取有效的注意力矩阵,用以确定各分块对额外语义表征的贡献。此外,我们为新增任务设计了异步更新机制,旨在引导模型有效聚焦于特定分块。在两个不同的中文地理重排序数据集上的实验表明,Geo-Encoder相比现有最优基线取得了显著提升。值得注意的是,它大幅提升了MGEO-BERT的Hit@1指标,在GeoTES数据集上从62.76提升至68.98,涨幅达6.22%。

英文摘要:

Chinese geographic re-ranking task aims to find the most relevant addresses among retrieved candidates, which is crucial for location-related services such as navigation maps. Unlike the general sentences, geographic contexts are closely intertwined with geographical concepts, from general spans (e.g., province) to specific spans (e.g., road). Given this feature, we propose an innovative framework, namely Geo-Encoder, to more effectively integrate Chinese geographical semantics into re-ranking pipelines. Our methodology begins by employing off-the-shelf tools to associate text with geographical spans, treating them as chunking units. Then, we present a multi-task learning module to simultaneously acquire an effective attention matrix that determines chunk contributions to extra semantic representations. Furthermore, we put forth an asynchronous update mechanism for the proposed addition task, aiming to guide the model capable of effectively focusing on specific chunks. Experiments on two distinct Chinese geographic re-ranking datasets, show that the Geo-Encoder achieves significant improvements when compared to state-of-the-art baselines. Notably, it leads to a substantial improvement in the Hit@1 score of MGEO-BERT, increasing it by 6.22% from 62.76 to 68.98 on the GeoTES dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑