Deep Conversational Recommender in Travel

TL;DR

This paper introduces a Deep Conversational Recommender system for travel that combines seq2seq models, neural latent topics, GCNs, and pointer networks to improve multi-turn, constraint-aware travel dialogue responses.

Contribution

The paper presents a novel deep conversational recommender integrating topic control, graph-based venue relationships, and pointer networks for travel domain dialogues.

Findings

Achieves superior performance over baseline models.

Effectively incorporates user constraints like price and distance.

Enhances response relevance and informativeness.

Abstract

When traveling to a foreign country, we are often in dire need of an intelligent conversational agent to provide instant and informative responses to our various queries. However, to build such a travel agent is non-trivial. First of all, travel naturally involves several sub-tasks such as hotel reservation, restaurant recommendation and taxi booking etc, which invokes the need for global topic control. Secondly, the agent should consider various constraints like price or distance given by the user to recommend an appropriate venue. In this paper, we present a Deep Conversational Recommender (DCR) and apply to travel. It augments the sequence-to-sequence (seq2seq) models with a neural latent topic component to better guide response generation and make the training easier. To consider the various constraints for venue recommendation, we leverage a graph convolutional network (GCN) based approach to capture the relationships between different venues and the match between venue and dialog context. For response generation, we combine the topic-based component with the idea of pointer networks, which allows us to effectively incorporate recommendation results. We perform extensive evaluation on a multi-turn task-oriented dialog dataset in travel domain and the results show that our method achieves superior performance as compared to a wide range of baselines.