Saved in:
Bibliographic Details
Main Authors: Faille, Juliette, Brabant, Quentin, Lecorve, Gwenole, Rojas-Barahona, Lina M., Gardent, Claire
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.07836
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911836318728192
author Faille, Juliette
Brabant, Quentin
Lecorve, Gwenole
Rojas-Barahona, Lina M.
Gardent, Claire
author_facet Faille, Juliette
Brabant, Quentin
Lecorve, Gwenole
Rojas-Barahona, Lina M.
Gardent, Claire
contents We explore question generation in the context of knowledge-grounded dialogs focusing on explainability and evaluation. Inspired by previous work on planning-based summarisation, we present a model which instead of directly generating a question, sequentially predicts first a fact then a question. We evaluate our approach on 37k test dialogs adapted from the KGConv dataset and we show that, although more demanding in terms of inference, our approach performs on par with a standard model which solely generates a question while allowing for a detailed referenceless evaluation of the model behaviour in terms of relevance, factuality and pronominalisation.
format Preprint
id arxiv_https___arxiv_org_abs_2404_07836
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Question Generation in Knowledge-Driven Dialog: Explainability and Evaluation
Faille, Juliette
Brabant, Quentin
Lecorve, Gwenole
Rojas-Barahona, Lina M.
Gardent, Claire
Computation and Language
We explore question generation in the context of knowledge-grounded dialogs focusing on explainability and evaluation. Inspired by previous work on planning-based summarisation, we present a model which instead of directly generating a question, sequentially predicts first a fact then a question. We evaluate our approach on 37k test dialogs adapted from the KGConv dataset and we show that, although more demanding in terms of inference, our approach performs on par with a standard model which solely generates a question while allowing for a detailed referenceless evaluation of the model behaviour in terms of relevance, factuality and pronominalisation.
title Question Generation in Knowledge-Driven Dialog: Explainability and Evaluation
topic Computation and Language
url https://arxiv.org/abs/2404.07836