Location Aware Modular Biencoder for Tourism Question Answering

TL;DR

This paper introduces a location-aware modular biencoder that encodes questions and POIs separately for efficient tourism question answering, leveraging dense vector retrieval and spatial reasoning to outperform previous methods.

Contribution

It presents a novel modular biencoder architecture with separate encoders for questions and POIs, improving efficiency and scalability in tourism QA tasks.

Findings

Outperforms previous methods across all metrics

Enables search space expansion by 20 times

Effective use of pretrained language models and spatial encoding

Abstract

Answering real-world tourism questions that seek Point-of-Interest (POI) recommendations is challenging, as it requires both spatial and non-spatial reasoning, over a large candidate pool. The traditional method of encoding each pair of question and POI becomes inefficient when the number of candidates increases, making it infeasible for real-world applications. To overcome this, we propose treating the QA task as a dense vector retrieval problem, where we encode questions and POIs separately and retrieve the most relevant POIs for a question by utilizing embedding space similarity. We use pretrained language models (PLMs) to encode textual information, and train a location encoder to capture spatial information of POIs. Experiments on a real-world tourism QA dataset demonstrate that our approach is effective, efficient, and outperforms previous methods across all metrics. Enabled by the dense retrieval architecture, we further build a global evaluation baseline, expanding the search space by 20 times compared to previous work. We also explore several factors that impact on the model's performance through follow-up experiments. Our code and model are publicly available at https://github.com/haonan-li/LAMB.