Improving Controllability of Educational Question Generation by ...

Title:Improving Controllability of Educational Question Generation by Keyword Provision ... Abstract: Question Generation (QG) receives increasing ...

Improving Controllability of Educational Question Generation by Keyword Provision · Ying-Hong Chan, Ho-Lam Chung, Yao-Chung Fan · Published in arXiv.org 2 ...

(PDF) Improving Controllability of Educational Question Generation ...

PDF | Question Generation (QG) receives increasing research attention in NLP community. One motivation for QG is that QG significantly facilitates the.

Towards Enriched Controllability for Educational Question Generation

fact, whereas implicit questions rely on summarizing3 and drawing inferences. 3 Summarization skills have been used to assess and improve students' reading com-.

Keyword Provision Question Generation for Facilitating Educational ...

Question Generation (QG) receives increasing research attention in the NLP ... way to control which question to generate. Second, questions generated ...

Ying-Hong Chan | Papers With Code

Improving Controllability of Educational Question Generation by Keyword Provision ... While the significant advancement of QG techniques was reported, current QG ...

Towards Enriched Controllability for Educational Question Generation

Recent work on QG aims to control the type of generated questions so that they meet educational needs. A remarkable example of controllability in educational QG ...

‪Ying-Hong Chan‬ - ‪Google 學術搜尋‬

Improving controllability of educational question generation by keyword provision. YH Chan, HL Chung, YC Fan. arXiv preprint arXiv:2112.01012, 2021. 3, 2021.

An LLM-Guided Method for Controllable Question Generation

In the field of education, for better assessment of students' abilities, generated questions often need to meet experts' requirements, indicating the need ...

Yao-Chung Fan | Papers With Code

Improving Controllability of Educational Question Generation by Keyword Provision · no code implementations • 2 Dec 2021 • Ying-Hong Chan, Ho-Lam Chung, Yao- ...

How Teachers Can Use Large Language Models and Bloom's ...

This study aims to enrich controllability in QG by introducing a new guidance attribute: question explicitness. We propose to control the generation of explicit ...

Towards Enriched Controllability for Educational Question Generation

A remarkable example of controllability in educational QG is the generation of questions underlying certain narrative elements, e.g., causal relationship, ...

bernardoleite/question-generation-control - GitHub

Recent work on QG aims to control the type of generated questions so that they meet educational needs. A remarkable example of controllability in educational QG ...

Towards Enriched Controllability for Educational Question Generation

This study proposes to control the generation of explicit and implicit wh-questions from children-friendly stories via question explicitness ...

similar - arxiv-sanity

Recent work on QG aims to control the type of generated questions so that they meet educational needs. A remarkable example of controllability in educational QG ...

Analysis of LLMs for educational question classification and ...

Multiple prompt variations followed by voting enhance robustness and improve the performance of question classification. •. ChatGPT performs better at ...

Review on Neural Question Generation for Education Purposes

Automatic question generation is expected to facilitate the generation of not only fluent and relevant but also educationally valuable questions ...

CQuAE: A new Contextualized QUestion Answering corpus on ...

Generating education-related questions and answers remains an open issue while being useful for students, teachers, and teaching aids.

Controllable Open-ended Question Generation with A New Question ...

tion and question generation while learning task- specific knowledge. It is ... to improve controllability and generation diver- sity: one using pre ...

Towards Human-Like Educational Question Generation with Large ...

While PLMs have shown increasing promise in a wide range of natural language applications, including question generation, they can generate unreliable and ...