Answering POI-Recommendation Questions for Tourism

Abstract

We introduce the novel and challenging task of answering Points-of-interest (POI) recommendation questions, using a collection of reviews that describe candidate answer entities (POIs). We harvest a QA dataset that contains 47,124 paragraph-sized real user questions from travelers seeking POI recommendations for hotels, attractions and restaurants. Each question can have thousands of candidate entities to choose from and each candidate is associated with a collection of unstructured reviews. Questions can include requirements based on physical location, budget, timings as well as other subjective considerations related to ambience, quality of service etc. We find that commonly used neural architectures for QA are prohibitively expensive for reasoning over the large number of candidate answer entities found in our dataset (over 5300 per question on average). Further, commonly used retriever-ranker based methods also do not work well for our task due to the nature of review-documents. Thus, as a first attempt at addressing some of the novel challenges of reasoning-at-scale posed by our task, we present a task specific baseline model that uses a three-stage cluster-select-rerank architecture. The model first clusters text for each entity to identify exemplar sentences describing an entity. It then uses a neural information retrieval (IR) module to select a set of potential entities from the large candidate set. A reranker uses a deeper attention-based architecture to pick the best answers from the selected entities. This strategy performs better than a pure IR or a pure attention-based reasoning approach yielding nearly 25% relative improvement in Accuracy@3 over both approaches.