Filters








1,562 Hits in 2.7 sec

Learning to Ask Unanswerable Questions for Machine Reading Comprehension

Haichao Zhu, Li Dong, Furu Wei, Wenhui Wang, Bing Qin, Ting Liu
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Machine reading comprehension with unanswerable questions is a challenging task.  ...  We also present a way to construct training data for our question generation models by leveraging the existing reading comprehension dataset.  ...  Acknowledgments We thank anonymous reviewers for their helpful comments. Qin and Liu were supported by National Natural Science Foundation of China (NSFC) via grants 61632011 and 61772156.  ... 
doi:10.18653/v1/p19-1415 dblp:conf/acl/ZhuDWWQL19 fatcat:biioiptm65bzznmmcbxqaqlqi4

VLSP 2021 - ViMRC Challenge: Vietnamese Machine Reading Comprehension [article]

Kiet Van Nguyen, Son Quoc Tran, Luan Thanh Nguyen, Tin Van Huynh, Son T. Luu, Ngan Luu-Thuy Nguyen
2022 arXiv   pre-print
One of the emerging research trends in natural language understanding is machine reading comprehension (MRC) which is the task to find answers to human questions based on textual data.  ...  The UIT-ViQuAD 2.0 dataset motivates researchers to further explore the Vietnamese machine reading comprehension task and related tasks such as question answering, question generation, and natural language  ...  Acknowledgments The authors would like to thank the team of aihub.vn 4 , and the annotators for their hard work to support the VLSP 2021 -ViMRC Challenge. The 4 https://aihub.vn/  ... 
arXiv:2203.11400v3 fatcat:yu6qxncb2ncozd3ahyomqif234

Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure [article]

Jiaqi Li, Ming Liu, Min-Yen Kan, Zihao Zheng, Zekun Wang, Wenqiang Lei, Ting Liu, Bing Qin
2020 arXiv   pre-print
We present the Molweni dataset, a machine reading comprehension (MRC) dataset with discourse structure built over multiparty dialog.  ...  We annotate 30,066 questions on this corpus, including both answerable and unanswerable questions.  ...  Thanks to Wenpeng Hu, a Ph.D. student of Peking University, for providing preprocessed Ubuntu data.  ... 
arXiv:2004.05080v3 fatcat:d4qzhd63obhvpnh2mxa53akpry

Question Answering Systems and Inclusion: Pros and Cons

Victoria Firsanova
2021 International Conference "Internet and Modern Society"  
In the inclusion, automated QA might become an effective tool allowing, for example, to ask questions about the interaction between neurotypical and atypical people anonymously and get reliable information  ...  Before the integration of QA in the inclusion, a research is required to prevent the generation of misleading and false answers, and verify that a system is safe and does not misrepresent or alter the  ...  That complicates the reading comprehension task by inviting the model to learn how to distinguish answerable questions from unanswerable ones and thus achieve higher accuracy in its analysis.  ... 
dblp:conf/ims2/Firsanova21 fatcat:nhinfisrqbanhpgeegt6yumuyq

Read + Verify: Machine Reading Comprehension with Unanswerable Questions [article]

Minghao Hu, Furu Wei, Yuxing Peng, Zhen Huang, Nan Yang, Dongsheng Li
2018 arXiv   pre-print
Machine reading comprehension with unanswerable questions aims to abstain from answering when no answer can be inferred.  ...  In addition to extract answers, previous works usually predict an additional "no-answer" probability to detect unanswerable cases.  ...  Acknowledgments We would like to thank Pranav Rajpurkar and Robin Jia for their helps with SQuAD 2.0 submissions.  ... 
arXiv:1808.05759v5 fatcat:shyxpkpxqvfobmhmxras2deswy

Know What You Don't Know: Unanswerable Questions for SQuAD

Pranav Rajpurkar, Robin Jia, Percy Liang
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
Extractive reading comprehension systems can often locate the correct answer to a question in a context document, but they also tend to make unreliable guesses on questions for which the correct answer  ...  Existing datasets either focus exclusively on answerable questions, or use automatically generated unanswerable questions that are easy to identify.  ...  We would like to thank the anonymous reviewers, Arun Chaganty, Peng Qi, and Sharon Zhou for their constructive feedback.  ... 
doi:10.18653/v1/p18-2124 dblp:conf/acl/RajpurkarJL18 fatcat:yufebgmovzemvh464rf2mckmvq

CJRC: A Reliable Human-Annotated Benchmark DataSet for Chinese Judicial Reading Comprehension [chapter]

Xingyi Duan, Baoxin Wang, Ziyue Wang, Wentao Ma, Yiming Cui, Dayong Wu, Shijin Wang, Ting Liu, Tianxiang Huo, Zhen Hu, Heng Wang, Zhiyuan Liu
2019 Lecture Notes in Computer Science  
By contrast, machine reading comprehension technology can quickly extract elements by answering various questions from the long document. We build two strong baseline models based on BERT and BiDAF.  ...  We present a Chinese judicial reading comprehension (CJRC) dataset which contains approximately 10K documents and almost 50K questions with answers.  ...  -The performance of some powerful baselines indicates there is enough space for improvement compared to human annotators. 2 Related Work Reading Comprehension Datasets Machine reading comprehension (  ... 
doi:10.1007/978-3-030-32381-3_36 fatcat:jsyu36ricnggzlkddermwnqwru

Know What You Don't Know: Unanswerable Questions for SQuAD [article]

Pranav Rajpurkar, Robin Jia, Percy Liang
2018 arXiv   pre-print
Extractive reading comprehension systems can often locate the correct answer to a question in a context document, but they also tend to make unreliable guesses on questions for which the correct answer  ...  Existing datasets either focus exclusively on answerable questions, or use automatically generated unanswerable questions that are easy to identify.  ...  We would like to thank the anonymous reviewers, Arun Chaganty, Peng Qi, and Sharon Zhou for their constructive feedback.  ... 
arXiv:1806.03822v1 fatcat:gvlphcyi5jbabcgizoe4rgbgiu

Neural Machine Reading Comprehension: Methods and Trends

Shanshan Liu, Xin Zhang, Sheng Zhang, Hui Wang, Weiming Zhang
2019 Applied Sciences  
Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques  ...  Although research on MRC based on deep learning is flourishing, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this  ...  Machine Reading Comprehension Given the context C and question Q, machine reading comprehension tasks ask the model to give the correct answer A to the question Q by learning the function F such that A  ... 
doi:10.3390/app9183698 fatcat:bpwwfikrpvh4dhphyl3ezpnn5e

Read + Verify: Machine Reading Comprehension with Unanswerable Questions

Minghao Hu, Furu Wei, Yuxing Peng, Zhen Huang, Nan Yang, Dongsheng Li
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Machine reading comprehension with unanswerable questions aims to abstain from answering when no answer can be inferred.  ...  In addition to extract answers, previous works usually predict an additional "no-answer" probability to detect unanswerable cases.  ...  Acknowledgments We would like to thank Pranav Rajpurkar and Robin Jia for their helps with SQuAD 2.0 submissions.  ... 
doi:10.1609/aaai.v33i01.33016529 fatcat:cqw3bgrxofbnnaoykuihcd2vem

To Answer or Not to Answer? Improving Machine Reading Comprehension Model with Span-based Contrastive Learning [article]

Yunjie Ji, Liangyu Chen, Chenxiao Dou, Baochang Ma, Xiangang Li
2022 arXiv   pre-print
Machine Reading Comprehension with Unanswerable Questions is a difficult NLP task, challenged by the questions which can not be answered from passages.  ...  To address this problem, in this paper, we propose a span-based method of Contrastive Learning (spanCL) which explicitly contrast answerable questions with their answerable and unanswerable counterparts  ...  Approach In this section, we first introduce the task of Machine Reading Comprehension with Unanswerable Questions (MRC-U). Then, a baseline MRC model based on PLM is described.  ... 
arXiv:2208.01299v1 fatcat:neklbnc3z5exnhm2zaiqmypf3i

FQuAD2.0: French Question Answering and knowing that you know nothing [article]

Quentin Heinrich, Gautier Viaud, Wacim Belblidia
2021 arXiv   pre-print
In 2020, as a first strong initiative to bridge the gap to the French language, Illuin Technology introduced FQuAD1.1, a French Native Reading Comprehension dataset composed of 60,000+ questions and answers  ...  Question Answering, including Reading Comprehension, is one of the NLP research areas that has seen significant scientific breakthroughs over the past few years, thanks to the concomitant advances in Language  ...  Our thanks also go to Inès Multrier for her contribution and insights on multilingual experiments.  ... 
arXiv:2109.13209v1 fatcat:3wwmd7r4kzcyjdjwvldnywq2xu

First-principle study on honeycomb fluorated-InTe monolayer with large Rashba spin splitting and direct bandgap

Kaixuan Li, Xiujuan Xian, Jiafu Wang, Niannian Yu
2019 Applied Surface Science  
Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques  ...  Although research on MRC based on deep learning is flourishing, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this  ...  Conclusion This article presents a comprehensive survey on the progresses of neural machine reading comprehension.  ... 
doi:10.1016/j.apsusc.2018.11.214 fatcat:dg2eusl7ufhttcsqlllyiisxb4

U-Net: Machine Reading Comprehension with Unanswerable Questions [article]

Fu Sun, Linyang Li, Xipeng Qiu, Yang Liu
2018 arXiv   pre-print
Machine reading comprehension with unanswerable questions is a new challenging task for natural language processing. A key subtask is to reliably predict whether the question is unanswerable.  ...  Different from the state-of-art pipeline models, U-Net can be learned in an end-to-end fashion.  ...  Acknowledgement We would like to thank Robin Jia, Pranav Rajpurkar for their help with SQuAD 2.0 submissions.  ... 
arXiv:1810.06638v1 fatcat:r5xzwlyrwndz7kaonkabauexei

Improving Machine Reading Comprehension via Adversarial Training [article]

Ziqing Yang, Yiming Cui, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu
2019 arXiv   pre-print
In this paper, we aim to apply AT on machine reading comprehension (MRC) and study its effects from multiple perspectives.  ...  We experiment with three different kinds of RC tasks: span-based RC, span-based RC with unanswerable questions and multi-choice RC.  ...  Lastly, by a careful analysis of the effect of adversarial training on different sets of examples, we found that AT helps the model to learn better on the examples with more rare words.  ... 
arXiv:1911.03614v1 fatcat:4jbgoplp2zajfbeb4ci6qyj5wa
« Previous Showing results 1 — 15 out of 1,562 results