Exploring Conversational Language Generation for Rich Content about Hotels

TL;DR

This paper investigates how to generate natural hotel dialogues by leveraging rich content and stylistic modeling, moving beyond simplified attribute-focused systems to produce more engaging conversational content.

Contribution

It introduces three experiments for collecting data and analyzing stylistic differences between webpage descriptions and conversational utterances for hotel dialogues.

Findings

Original hotel descriptions differ stylistically from conversational data.

Quantified stylistic features can inform generation and scoring models.

Rich hotel content requires new NLG methods for natural dialogue generation.

Abstract

Dialogue systems for hotel and tourist information have typically simplified the richness of the domain, focusing system utterances on only a few selected attributes such as price, location and type of rooms. However, much more content is typically available for hotels, often as many as 50 distinct instantiated attributes for an individual entity. New methods are needed to use this content to generate natural dialogues for hotel information, and in general for any domain with such rich complex content. We describe three experiments aimed at collecting data that can inform an NLG for hotels dialogues, and show, not surprisingly, that the sentences in the original written hotel descriptions provided on webpages for each hotel are stylistically not a very good match for conversational interaction. We quantify the stylistic features that characterize the differences between the original textual data and the collected dialogic data. We plan to use these in stylistic models for generation, and for scoring retrieved utterances for use in hotel dialogues