Automatic Answerability Evaluation for Question Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Zifan, Funakoshi, Kotaro, Okumura, Manabu
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917596615409664
author Wang, Zifan
Funakoshi, Kotaro
Okumura, Manabu
author_facet Wang, Zifan
Funakoshi, Kotaro
Okumura, Manabu
contents Conventional automatic evaluation metrics, such as BLEU and ROUGE, developed for natural language generation (NLG) tasks, are based on measuring the n-gram overlap between the generated and reference text. These simple metrics may be insufficient for more complex tasks, such as question generation (QG), which requires generating questions that are answerable by the reference answers. Developing a more sophisticated automatic evaluation metric, thus, remains an urgent problem in QG research. This work proposes PMAN (Prompting-based Metric on ANswerability), a novel automatic evaluation metric to assess whether the generated questions are answerable by the reference answers for the QG tasks. Extensive experiments demonstrate that its evaluation results are reliable and align with human evaluations. We further apply our metric to evaluate the performance of QG models, which shows that our metric complements conventional metrics. Our implementation of a GPT-based QG model achieves state-of-the-art performance in generating answerable questions.
format Preprint
id arxiv_https___arxiv_org_abs_2309_12546
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Automatic Answerability Evaluation for Question Generation
Wang, Zifan
Funakoshi, Kotaro
Okumura, Manabu
Computation and Language
Conventional automatic evaluation metrics, such as BLEU and ROUGE, developed for natural language generation (NLG) tasks, are based on measuring the n-gram overlap between the generated and reference text. These simple metrics may be insufficient for more complex tasks, such as question generation (QG), which requires generating questions that are answerable by the reference answers. Developing a more sophisticated automatic evaluation metric, thus, remains an urgent problem in QG research. This work proposes PMAN (Prompting-based Metric on ANswerability), a novel automatic evaluation metric to assess whether the generated questions are answerable by the reference answers for the QG tasks. Extensive experiments demonstrate that its evaluation results are reliable and align with human evaluations. We further apply our metric to evaluate the performance of QG models, which shows that our metric complements conventional metrics. Our implementation of a GPT-based QG model achieves state-of-the-art performance in generating answerable questions.
title Automatic Answerability Evaluation for Question Generation
topic Computation and Language
url https://arxiv.org/abs/2309.12546