paper-with-me

홈 › Papers

MixQG: Neural Question Generation with Mixed Answer Types

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Asking good questions is an essential ability for both human and machine intelligence. However, existing neural question generation approaches mainly focus on short factoid type of answers. In this paper, we introduce a neural question generator, MixQG, to bridge this gap. We combine nine question answering datasets with diverse answer types, including yes/no, multiple-choice, extractive, and abstractive answers, to train a single generative model. We show with empirical results that our model outperforms existing work in both seen and unseen domains, and can generate questions with different cognitive levels when conditioned on different answer types. We run a human evaluation study to assess the quality of generated questions and find that MixQG outperforms the next best model by 10%. Our code and model checkpoints will be released and integrated with the HuggingFace library to facilitate various downstream applications.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multiple-choiceQuestion AnsweringQuestion GenerationQuestion-Generation

Similar Papers 제목 키워드 기반

MixQG: Neural Question Generation with Mixed Answer Types

2021-10-15 · Findings (NAACL) 2022 7 · Lidiya Murakhovs'ka, Chien-Sheng Wu, Philippe Laban, Tong Niu 외

Asking good questions is an essential ability for both human and machine intelligence. However, existing neural question generation approaches mainly focus on the short factoid type of answers. In this paper, we propose …

Multiple-choiceQuestion AnsweringQuestion GenerationQuestion-Generation

Uncovering Code-Mixed Challenges: A Framework for Linguistically Driven Question Generation and Neural Based Question Answering

2018-10-01 · CONLL 2018 10 · Deepak Gupta, Pabitra Lenka, Asif Ekbal, Pushpak Bhattacharyya

Existing research on question answering (QA) and comprehension reading (RC) are mainly focused on the resource-rich language like English. In recent times, the rapid growth of multi-lingual web content has posed several …

Question AnsweringQuestion GenerationQuestion-Generation

DCN+: Mixed Objective and Deep Residual Coattention for Question Answering

2017-10-31 · ICLR 2018 1 · Caiming Xiong, Victor Zhong, Richard Socher

Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometimes equally accurate. We propose a mixed …

Question Answering

INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions

2022-07-02 · Zeqiu Wu, Ryu Parish, Hao Cheng, Sewon Min 외

In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the available knowledge sources…

Open-Domain Question AnsweringQuestion AnsweringResponse Generation

TrustUQA: A Trustful Framework for Unified Structured Data Question Answering

2024-06-27 · Wen Zhang, Long Jin, Yushan Zhu, Jiaoyan Chen 외

Natural language question answering (QA) over structured data sources such as tables and knowledge graphs have been widely investigated, especially with Large Language Models (LLMs) in recent years. The main solutions in…

Answer GenerationKnowledge GraphsQuestion AnsweringRetrieval