paper-with-me

홈 › Papers

Evaluating for Diversity in Question Generation over Text

2020-08-17 · Michael Sejr Schlichtkrull, Weiwei Cheng

Generating diverse and relevant questions over text is a task with widespread applications. We argue that commonly-used evaluation metrics such as BLEU and METEOR are not suitable for this task due to the inherent diversity of reference questions, and propose a scheme for extending conventional metrics to reflect diversity. We furthermore propose a variational encoder-decoder model for this task. We show through automatic and human evaluation that our variational model improves diversity without loss of quality, and demonstrate how our evaluation scheme reflects this improvement.

📄 PDF Abstract BibTeX arXiv:2008.07291

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderDiversityQuestion GenerationQuestion-Generation

Similar Papers 제목 키워드 기반

Diversity and Consistency: Exploring Visual Question-Answer Pair Generation

2021-11-01 · Findings (EMNLP) 2021 11 · Sen yang, Qingyu Zhou, Dawei Feng, Yang Liu 외

Although showing promising values to downstream applications, generating question and answer together is under-explored. In this paper, we introduce a novel task that targets question-answer pair generation from visual i…

DiversityQuestion AnsweringQuestion GenerationQuestion-Generation+3

Evaluating the Evaluation of Diversity in Natural Language Generation

2020-04-06 · EACL 2021 2 · Guy Tevet, Jonathan Berant

Despite growing interest in natural language generation (NLG) models that produce diverse outputs, there is currently no principled method for evaluating the diversity of an NLG system. In this work, we propose a framewo…

DiversityText Generation

Diversify Question Generation with Continuous Content Selectors and Question Type Modeling

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Zhen Wang, Siwei Rao, Jie Zhang, Zhen Qin 외

Generating questions based on answers and relevant contexts is a challenging task. Recent work mainly pays attention to the quality of a single generated question. However, question generation is actually a one-to-many p…

DiversityQuestion GenerationQuestion-GenerationVocal Bursts Type Prediction

On the Importance of Diversity in Question Generation for QA

2020-07-01 · ACL 2020 6 · Md. Arafat Sultan, Ch, Shubham el, Fern 외

Automatic question generation (QG) has shown promise as a source of synthetic training data for question answering (QA). In this paper we ask: Is textual diversity in QG beneficial for downstream QA? Using top-p nucleus …

DiversityQuestion AnsweringQuestion GenerationQuestion-Generation

Diversifying Question Generation over Knowledge Base via External Natural Questions

2023-09-23 · Shasha Guo, Jing Zhang, Xirui Ke, Cuiping Li 외

Previous methods on knowledge base question generation (KBQG) primarily focus on enhancing the quality of a single generated question. Recognizing the remarkable paraphrasing ability of humans, we contend that diverse te…

DiversityNatural QuestionsQuestion AnsweringQuestion Generation+1