arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.04283cs.CL
收藏

MGeo:多模态地理预训练方法

MGeo: Multi-Modal Geographic Pre-Training Method

Damo Academy(达摩院);Alibaba Group(阿里巴巴集团);Gaode Map(高德地图)

Ruixue Ding, Boli Chen, Pengjun Xie, Fei Huang, Xin Li, Qiang Zhang, Yao Xu

AI总结:

本文提出多模态地理语言模型MGeo,通过将地理上下文表示为新模态并利用地理编码器与多模态交互模块提取相关性,显著提升了查询与POI匹配能力,并构建了开源大规模基准GeoTES。

摘要:

作为基于位置的服务(LBS,例如导航地图)中的核心任务,查询与兴趣点(POI)匹配将用户的意图与现实世界的地理信息连接起来。近年来,预训练模型(PTMs)在许多自然语言处理(NLP)任务中取得了进展。然而,基于通用文本的PTMs缺乏足够的地理知识来进行查询-POI匹配。为了克服这一局限性,相关文献尝试基于地理相关语料库采用领域自适应预训练。但是,查询通常包含对多个地理对象的提及,例如附近的道路和感兴趣区域(ROIs)。因此,地理上下文(GC),即这些多样的地理对象及其关系,对于检索最相关的POI至关重要。单模态PTMs几乎无法利用重要的GC,因此性能受限。在本研究中,我们提出了一种新颖的查询-POI匹配方法——多模态地理语言模型(MGeo),它包含一个地理编码器和一个多模态交互模块。MGeo将GC表示为一种新的模态,并能够充分提取多模态相关性以实现准确的查询-POI匹配。此外,该主题目前尚无公开可用的基准。为了促进进一步的研究,我们构建了一个新的开源大规模基准——地理文本相似度(GeoTES)。其中的POIs来自开源地理信息系统(GIS)。查询由标注者手动生成,以防止隐私问题。与几个强基线相比,在GeoTES上的广泛实验结果和详细的消融分析表明,我们提出的多模态预训练方法能够显著提升通用PTMs的查询-POI匹配能力,即使查询的GC未被提供时也是如此。我们的代码和数据集已在 https://github.com/PhantomGrapes/MGeo 上公开。

英文摘要:

As a core task in location-based services (LBS) (e.g., navigation maps), query and point of interest (POI) matching connects users' intent with real-world geographic information. Recently, pre-trained models (PTMs) have made advancements in many natural language processing (NLP) tasks. Generic text-based PTMs do not have enough geographic knowledge for query-POI matching. To overcome this limitation, related literature attempts to employ domain-adaptive pre-training based on geo-related corpus. However, a query generally contains mentions of multiple geographic objects, such as nearby roads and regions of interest (ROIs). The geographic context (GC), i.e., these diverse geographic objects and their relationships, is therefore pivotal to retrieving the most relevant POI. Single-modal PTMs can barely make use of the important GC and therefore have limited performance. In this work, we propose a novel query-POI matching method Multi-modal Geographic language model (MGeo), which comprises a geographic encoder and a multi-modal interaction module. MGeo represents GC as a new modality and is able to fully extract multi-modal correlations for accurate query-POI matching. Besides, there is no publicly available benchmark for this topic. In order to facilitate further research, we build a new open-source large-scale benchmark Geographic TExtual Similarity (GeoTES). The POIs come from an open-source geographic information system (GIS). The queries are manually generated by annotators to prevent privacy issues. Compared with several strong baselines, the extensive experiment results and detailed ablation analyses on GeoTES demonstrate that our proposed multi-modal pre-training method can significantly improve the query-POI matching capability of generic PTMs, even when the queries' GC is not provided. Our code and dataset are publicly available at https://github.com/PhantomGrapes/MGeo.

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。

↑