EMNLP Findings2023
Natural Response Generation for Chinese Reading Comprehension
Nuo Chen, Hongguang Li, Yinan Bao, Baoyuan Wang, Jia Li
Abstract
Machine reading comprehension (MRC) is an important area of conversation agents and draws a lot of attention. However, there is a notable limitation to current MRC benchmarks: The labeled answers are mostly either spans extracted from the target corpus or the choices of the given candidates, ignoring the natural aspect of high-quality responses. As a result, MRC models trained on these datasets can not generate human-like responses in real QA scenarios. To this end, we construct a new dataset called Penguin to promote the research of MRC, providing a training and test bed for natural response generation to real scenarios. Concretely, Penguin consists of 200k training data with high-quality fluent, and well-informed responses. Penguin is the first benchmark towards natural response generation in Chinese MRC on a relatively large scale. To address the challenges in Penguin, we develop two strong baselines: endto-end and two-stage frameworks. Following that, we further design Prompt-BART: finetuning the pre-trained generative language models with a mixture of prefix prompts in Penguin. Extensive experiments validated the effectiveness of this design. Our benchmark and codes are available at https://github. com/nuochenpku/Penguin.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Finetuned Language Models are Zero-Shot Learners cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
- Finetuned Language Models are Zero-Shot Learners cites Language Models are Few-Shot Learners
Builds on8
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Finetuned Language Models are Zero-Shot LearnersJason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu et al.ICLR 2022 · 4,966 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question AnsweringChenyu You, Nuo Chen, Yuexian ZouEMNLP Findings 2021 · 43 citations
- ReCO: A Large Scale Chinese Reading Comprehension Dataset on OpinionBingning Wang, Ting Yao, Qi Zhang, Jingfang Xu et al.AAAI 2020 · 26 citations
Related papers
- Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading ComprehensionNuo Chen, Hongguang Li, Junqing He, Yinan Bao et al.EMNLP Findings 2023 · 2 citations
- Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering DataDian Yu, Kai Sun, Dong Yu, Claire CardieEMNLP Findings 2021 · 2 citations
- ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue SummarizationJiaan Wang, Fandong Meng, Ziyao Lu, Duo Zheng et al.EMNLP 2022 · 27 citations
- Span Selection Pre-training for Question AnsweringMichael R. Glass, Alfio Gliozzo, Rishav Chakravarti, Anthony Ferritto et al.ACL 2020 · 9 citations
- Why Machine Reading Comprehension Models Learn Shortcuts?Yuxuan Lai, Chen Zhang, Yansong Feng, Quzhe Huang et al.ACL Findings 2021 · 32 citations
