Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Empowering Air Travelers: A Chatbot for Canadian Air Passenger Rights

Maksym Taranukhin, Sahithya Ravi, Gabor Lukacs, Evangelos Milios, Vered Shwartz

TL;DR

A chatbot to assist passengers and educate them about their rights is presented, which breaks a complex user input into simple queries which are used to retrieve information from a collection of documents detailing air travel regulations.

Abstract

The Canadian air travel sector has seen a significant increase in flight delays, cancellations, and other issues concerning passenger rights. Recognizing this demand, we present a chatbot to assist passengers and educate them about their rights. Our system breaks a complex user input into simple queries which are used to retrieve information from a collection of documents detailing air travel regulations. The most relevant passages from these documents are presented along with links to the original documents and the generated queries, enabling users to dissect and leverage the information for their unique circumstances. The system successfully overcomes two predominant challenges: understanding complex user inputs, and delivering accurate answers, free of hallucinations, that passengers can rely on for making informed decisions. A user study comparing the chatbot to a Google search demonstrated the chatbot's usefulness and ease of use. Beyond the primary goal of providing accurate and timely information to air passengers regarding their rights, we hope that this system will also enable further research exploring the tradeoff between the user-friendly conversational interface of chatbots and the accuracy of retrieval systems.

Empowering Air Travelers: A Chatbot for Canadian Air Passenger Rights

TL;DR

A chatbot to assist passengers and educate them about their rights is presented, which breaks a complex user input into simple queries which are used to retrieve information from a collection of documents detailing air travel regulations.

Abstract

The Canadian air travel sector has seen a significant increase in flight delays, cancellations, and other issues concerning passenger rights. Recognizing this demand, we present a chatbot to assist passengers and educate them about their rights. Our system breaks a complex user input into simple queries which are used to retrieve information from a collection of documents detailing air travel regulations. The most relevant passages from these documents are presented along with links to the original documents and the generated queries, enabling users to dissect and leverage the information for their unique circumstances. The system successfully overcomes two predominant challenges: understanding complex user inputs, and delivering accurate answers, free of hallucinations, that passengers can rely on for making informed decisions. A user study comparing the chatbot to a Google search demonstrated the chatbot's usefulness and ease of use. Beyond the primary goal of providing accurate and timely information to air passengers regarding their rights, we hope that this system will also enable further research exploring the tradeoff between the user-friendly conversational interface of chatbots and the accuracy of retrieval systems.
Paper Structure (33 sections, 2 figures, 3 tables)

This paper contains 33 sections, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Chatbot Architecture
  3. Input Understanding
  4. Decontextualization.
  5. Decompositional Query Generation.
  6. Document Retrieval
  7. Answer Presentation
  8. Implementation Details
  9. Data Collection
  10. Web Application
  11. Backend.
  12. Frontend.
  13. Evaluation
  14. User Study
  15. Methodology.
  16. ...and 18 more sections

Figures (2)

  • Figure 1: User interface of the Air Passenger Rights chatbot.
  • Figure 2: Overall Architecture of the Air Passenger Chatbot exemplified on an input query from the user: We use a LLM to decontextualize and decompose a given query, and provide a response by retrieving the relevant passages to answer the simplified queries.