paper-with-me

홈 › Papers

Closed-book Question Generation via Contrastive Learning

2022-10-13 · Xiangjue Dong, Jiaying Lu, Jianling Wang, James Caverlee

Question Generation (QG) is a fundamental NLP task for many downstream applications. Recent studies on open-book QG, where supportive answer-context pairs are provided to models, have achieved promising progress. However, generating natural questions under a more practical closed-book setting that lacks these supporting documents still remains a challenge. In this work, we propose a new QG model for this closed-book setting that is designed to better understand the semantics of long-form abstractive answers and store more information in its parameters through contrastive learning and an answer reconstruction module. Through experiments, we validate the proposed QG model on both public datasets and a new WikiCQA dataset. Empirical results show that the proposed QG model outperforms baselines in both automatic evaluation and human evaluation. In addition, we show how to leverage the proposed model to improve existing question-answering systems. These results further indicate the effectiveness of our QG model for enhancing closed-book question-answering tasks.

📄 PDF Abstract BibTeX arXiv:2210.06781

Code (1)

dongxiangjue/closed-book-question-generation-via-contrastive-learning 공식 구현

Tasks

Contrastive LearningNatural QuestionsOpen-Domain Question AnsweringQuestion AnsweringQuestion GenerationQuestion-Generation

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Context Generation Improves Open Domain Question Answering

2022-10-12 · Dan Su, Mostofa Patwary, Shrimai Prabhumoye, Peng Xu 외

Closed-book question answering (QA) requires a model to directly answer an open-domain question without access to any external knowledge. Prior work on closed-book QA either directly finetunes or prompts a pretrained lan…

Language ModelingLanguage ModellingOpen-Domain Question AnsweringQuestion Answering

Query Refinement Prompts for Closed-Book Long-Form Question Answering

2022-10-31 · Reinald Kim Amplayo, Kellie Webster, Michael Collins, Dipanjan Das 외

Large language models (LLMs) have been shown to perform well in answering questions and in producing long-form texts, both in few-shot closed-book settings. While the former can be validated using well-known evaluation m…

FormLong Form Question AnsweringQuestion Answering

Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?

2021-06-03 · ACL 2021 5 · Cunxiang Wang, Pai Liu, Yue Zhang

Recent work has investigated the interesting question using pre-trained language models (PLMs) as knowledge bases for answering open questions. However, existing work is limited in using small benchmarks with high test-t…

Question Answering

Perhaps PTLMs Should Go to School – A Task to Assess Open Book and Closed Book QA

2021-10-01 · AKBC Workshop CSKB 2021 10 · Manuel Ciosici, Joe Cecil, Dong-Ho Lee, Alex Hedges 외

Our goal is to deliver a new task and leaderboard to stimulate research on question answering and pre-trained language models (PTLMs) to understand a significant instructional document, e.g., an introductory college text…

Question Answering

Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA

2021-10-04 · Manuel R. Ciosici, Joe Cecil, Alex Hedges, Dong-Ho Lee 외

Our goal is to deliver a new task and leaderboard to stimulate research on question answering and pre-trained language models (PTLMs) to understand a significant instructional document, e.g., an introductory college text…

Question Answering