@inproceedings{guo-etal-2024-diversifying,
title = "Diversifying Question Generation over Knowledge Base via External Natural Questions",
author = "Guo, Shasha and
Zhang, Jing and
Ke, Xirui and
Li, Cuiping and
Chen, Hong",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.454/",
pages = "5096--5108",
abstract = "Previous methods on knowledge base question generation (KBQG) primarily focus on refining the quality of a single generated question. However, considering the remarkable paraphrasing ability of humans, we believe that diverse texts can express identical semantics through varied expressions. The above insights make diversifying question generation an intriguing task, where the first challenge is evaluation metrics for diversity. Current metrics inadequately assess the aforementioned diversity. They calculate the ratio of unique n-grams in the generated question, which tends to measure duplication rather than true diversity. Accordingly, we devise a new diversity evaluation metric, which measures the diversity among top-k generated questions for each instance while ensuring their relevance to the ground truth. Clearly, the second challenge is how to enhance diversifying question generation. To address this challenge, we introduce a dual model framework interwoven by two selection strategies to generate diverse questions leveraging external natural questions. The main idea of our dual framework is to extract more diverse expressions and integrate them into the generation model to enhance diversifying question generation. Extensive experiments on widely used benchmarks for KBQG show that our approach can outperform pre-trained language model baselines and text-davinci-003 in diversity while achieving comparable performance with ChatGPT."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2024-diversifying">
<titleInfo>
<title>Diversifying Question Generation over Knowledge Base via External Natural Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shasha</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xirui</namePart>
<namePart type="family">Ke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cuiping</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous methods on knowledge base question generation (KBQG) primarily focus on refining the quality of a single generated question. However, considering the remarkable paraphrasing ability of humans, we believe that diverse texts can express identical semantics through varied expressions. The above insights make diversifying question generation an intriguing task, where the first challenge is evaluation metrics for diversity. Current metrics inadequately assess the aforementioned diversity. They calculate the ratio of unique n-grams in the generated question, which tends to measure duplication rather than true diversity. Accordingly, we devise a new diversity evaluation metric, which measures the diversity among top-k generated questions for each instance while ensuring their relevance to the ground truth. Clearly, the second challenge is how to enhance diversifying question generation. To address this challenge, we introduce a dual model framework interwoven by two selection strategies to generate diverse questions leveraging external natural questions. The main idea of our dual framework is to extract more diverse expressions and integrate them into the generation model to enhance diversifying question generation. Extensive experiments on widely used benchmarks for KBQG show that our approach can outperform pre-trained language model baselines and text-davinci-003 in diversity while achieving comparable performance with ChatGPT.</abstract>
<identifier type="citekey">guo-etal-2024-diversifying</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.454/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5096</start>
<end>5108</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Diversifying Question Generation over Knowledge Base via External Natural Questions
%A Guo, Shasha
%A Zhang, Jing
%A Ke, Xirui
%A Li, Cuiping
%A Chen, Hong
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F guo-etal-2024-diversifying
%X Previous methods on knowledge base question generation (KBQG) primarily focus on refining the quality of a single generated question. However, considering the remarkable paraphrasing ability of humans, we believe that diverse texts can express identical semantics through varied expressions. The above insights make diversifying question generation an intriguing task, where the first challenge is evaluation metrics for diversity. Current metrics inadequately assess the aforementioned diversity. They calculate the ratio of unique n-grams in the generated question, which tends to measure duplication rather than true diversity. Accordingly, we devise a new diversity evaluation metric, which measures the diversity among top-k generated questions for each instance while ensuring their relevance to the ground truth. Clearly, the second challenge is how to enhance diversifying question generation. To address this challenge, we introduce a dual model framework interwoven by two selection strategies to generate diverse questions leveraging external natural questions. The main idea of our dual framework is to extract more diverse expressions and integrate them into the generation model to enhance diversifying question generation. Extensive experiments on widely used benchmarks for KBQG show that our approach can outperform pre-trained language model baselines and text-davinci-003 in diversity while achieving comparable performance with ChatGPT.
%U https://aclanthology.org/2024.lrec-main.454/
%P 5096-5108
Markdown (Informal)
[Diversifying Question Generation over Knowledge Base via External Natural Questions](https://aclanthology.org/2024.lrec-main.454/) (Guo et al., LREC-COLING 2024)
ACL