Saved in:
Bibliographic Details
Main Authors: Väth, Dirk, Vanderlyn, Lindsey, Vu, Ngoc Thang
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.10227
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916176979820544
author Väth, Dirk
Vanderlyn, Lindsey
Vu, Ngoc Thang
author_facet Väth, Dirk
Vanderlyn, Lindsey
Vu, Ngoc Thang
contents Conversational interfaces provide a flexible and easy way for users to seek information that may otherwise be difficult or inconvenient to obtain. However, existing interfaces generally fall into one of two categories: FAQs, where users must have a concrete question in order to retrieve a general answer, or dialogs, where users must follow a predefined path but may receive a personalized answer. In this paper, we introduce Conversational Tree Search (CTS) as a new task that bridges the gap between FAQ-style information retrieval and task-oriented dialog, allowing domain-experts to define dialog trees which can then be converted to an efficient dialog policy that learns only to ask the questions necessary to navigate a user to their goal. We collect a dataset for the travel reimbursement domain and demonstrate a baseline as well as a novel deep Reinforcement Learning architecture for this task. Our results show that the new architecture combines the positive aspects of both the FAQ and dialog system used in the baseline and achieves higher goal completion while skipping unnecessary questions.
format Preprint
id arxiv_https___arxiv_org_abs_2303_10227
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Conversational Tree Search: A New Hybrid Dialog Task
Väth, Dirk
Vanderlyn, Lindsey
Vu, Ngoc Thang
Computation and Language
Artificial Intelligence
Machine Learning
Conversational interfaces provide a flexible and easy way for users to seek information that may otherwise be difficult or inconvenient to obtain. However, existing interfaces generally fall into one of two categories: FAQs, where users must have a concrete question in order to retrieve a general answer, or dialogs, where users must follow a predefined path but may receive a personalized answer. In this paper, we introduce Conversational Tree Search (CTS) as a new task that bridges the gap between FAQ-style information retrieval and task-oriented dialog, allowing domain-experts to define dialog trees which can then be converted to an efficient dialog policy that learns only to ask the questions necessary to navigate a user to their goal. We collect a dataset for the travel reimbursement domain and demonstrate a baseline as well as a novel deep Reinforcement Learning architecture for this task. Our results show that the new architecture combines the positive aspects of both the FAQ and dialog system used in the baseline and achieves higher goal completion while skipping unnecessary questions.
title Conversational Tree Search: A New Hybrid Dialog Task
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2303.10227