Know What You Don't Know: Unanswerable Questions for SQuAD
Pranav Rajpurkar,Robin Jia,Percy Liang +2 more
- 11 Jun 2018
- Vol. 2, pp 784-789
2.3K
TL;DR: SQuADRUn as discussed by the authors is a new dataset that combines the existing Stanford Question Answering Dataset with over 50,000 unanswerable questions written adversarially by crowdworkers to look similar to answerable ones.
read more
Abstract: 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 is not stated in the context. Existing datasets either focus exclusively on answerable questions, or use automatically generated unanswerable questions that are easy to identify. To address these weaknesses, we present SQuADRUn, a new dataset that combines the existing Stanford Question Answering Dataset (SQuAD) with over 50,000 unanswerable questions written adversarially by crowdworkers to look similar to answerable ones. To do well on SQuADRUn, systems must not only answer questions when possible, but also determine when no answer is supported by the paragraph and abstain from answering. SQuADRUn is a challenging natural language understanding task for existing models: a strong neural system that gets 86% F1 on SQuAD achieves only 66% F1 on SQuADRUn. We release SQuADRUn to the community as the successor to SQuAD.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
HisBERT for Conversational Reading Comprehension
Chuang Liu,Deyi Xiong,Yuxiang Jia,Hongying Zan,Changjian Hu +4 more
- 04 Dec 2020
TL;DR: In this paper, the authors propose to integrate conversation history into the architecture of BERT for conversational reading comprehension (CRC) by using adversarial training to disturb the word embedding layer, which improves the robustness of the proposed model.
7
Evaluating Deep Learning Techniques for Natural Language Inference
TL;DR: In this paper , the authors compare five deep learning models, such as BERT, RoBERTa, and ALBERT, on eight widely used NLI datasets, including the BreakingNLI dataset.
IDK-MRC: Unanswerable Questions for Indonesian Machine Reading Comprehension
Rifki Afina Putri,Alice Oh +1 more
- 01 Jan 2022
TL;DR: The lack of unanswerable questions in Indonesian Machine Reading Comprehension (MRC) datasets leads to poor model performance. IDK-MRC is a new dataset that includes a large number of unanswerable questions, improving the performance of Indonesian MRC models.
•Posted Content
Selective Question Answering under Domain Shift
TL;DR: In this paper, a QA model is tested on a mixture of in-domain and out-of-domain data, and must answer (i.e., not abstain on) as many questions as possible while maintaining high accuracy.
7
•Posted Content
Open-Domain Question-Answering for COVID-19 and Other Emergent Domains
TL;DR: In this article, an open-domain question-answering system for the emergent domain of COVID-19 has been proposed to find answers to free-text questions from a large set of documents.
7
References
Deep contextualized word representations
Matthew E. Peters,Mark Neumann,Mohit Iyyer,Matt Gardner,Christopher Clark,Kenton Lee,Luke Zettlemoyer +6 more
- 15 Feb 2018
TL;DR: This paper introduced a new type of deep contextualized word representation that models both complex characteristics of word use (e.g., syntax and semantics), and how these uses vary across linguistic contexts (i.e., to model polysemy).
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Pranav Rajpurkar,Jian Zhang,Konstantin Lopyrev,Percy Liang +3 more
- 16 Jun 2016
TL;DR: The Stanford Question Answering Dataset (SQuAD) as mentioned in this paper is a reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage.
6.3K
•Posted Content
SQuAD: 100,000+ Questions for Machine Comprehension of Text
TL;DR: The Stanford Question Answering Dataset (SQuAD) as mentioned in this paper is a reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage.
5.8K
A large annotated corpus for learning natural language inference
Samuel R. Bowman,Gabor Angeli,Christopher Potts,Christopher D. Manning +3 more
- 21 Aug 2015
TL;DR: The Stanford Natural Language Inference (SNLI) corpus as discussed by the authors is a large-scale collection of labeled sentence pairs, written by humans doing a novel grounded task based on image captioning.
•Proceedings Article
Teaching machines to read and comprehend
Karl Moritz Hermann,Tomáš Kočiský,Edward Grefenstette,Lasse Espeholt,Will Kay,Mustafa Suleyman,Phil Blunsom +6 more
- 07 Dec 2015
TL;DR: A new methodology is defined that resolves this bottleneck and provides large scale supervised reading comprehension data that allows a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure to be developed.