Open AccessPosted Content
Know What You Don't Know: Unanswerable Questions for SQuAD
TL;DR: SQuadRUn is 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.
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 SQuAD 2.0, the latest version of the Stanford Question Answering Dataset (SQuAD). SQuAD 2.0 combines existing SQuAD data with over 50,000 unanswerable questions written adversarially by crowdworkers to look similar to answerable ones. To do well on SQuAD 2.0, systems must not only answer questions when possible, but also determine when no answer is supported by the paragraph and abstain from answering. SQuAD 2.0 is a challenging natural language understanding task for existing models: a strong neural system that gets 86% F1 on SQuAD 1.1 achieves only 66% F1 on SQuAD 2.0.
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
Beware of Model Collapse! Fast and Stable Test-time Adaptation for Robust Question Answering
Yi Su,Yixin Ji,Juntao Li,Hai Ye,Min Zhang +4 more
TL;DR: This paper proposes Anti-CF, a fast and stable test-time adaptation method for robust question answering, addressing model collapse caused by imbalanced label distributions, achieving comparable results to previous methods with significant speedup.
3
Long-Tailed Question Answering in an Open World
Yinpei Dai,Hao Lang,Yinhe Zheng,Fei Huang,Yongbin Li +4 more
- 11 May 2023
TL;DR: The authors propose an Open Long-Tailed QA (OLTQA) model that encourages knowledge sharing between head, tail and unseen tasks, and explicitly mines knowledge from a large pre-trained language model.
Emerging trends: General fine-tuning (gft)
TL;DR: Gft (general fine-tuning), a little language for deep nets, introduced at an ACL-2022 tutorial, demystifies deep nets and makes deep nets accessible to a broad audience including non-programmers.
3
•Posted Content
Hierarchical Multitask Learning Approach for BERT.
TL;DR: This work adopts hierarchical multitask learning approaches for BERT pre- training, and shows that imposing a task hierarchy in pre-training improves the performance of embeddings.
3
Goal-guided Generative Prompt Injection Attack on Large Language Models
Chong Zhang,Mingyu Jin,Qinkai Yu,Chengzhi Liu,Haochen Xue,Xiaobo Jin +5 more
TL;DR: Goal-guided generative prompt injection attack on large language models maximizes the KL divergence between the conditional probabilities of the clean text and the adversarial text.
3
References
•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
•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.
•Proceedings Article
Bidirectional Attention Flow for Machine Comprehension
Minjoon Seo,Aniruddha Kembhavi,Ali Farhadi,Hannaneh Hajishirzi +3 more
- 04 Nov 2016
TL;DR: The BIDAF network is introduced, a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization.
2.1K
•Proceedings Article
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset.
Tri Nguyen,Mir Rosenberg,Xia Song,Jianfeng Gao,Saurabh Tiwary,Rangan Majumder,Li Deng +6 more
- 04 Nov 2016
TL;DR: MS MARCO as mentioned in this paper is a large scale dataset for reading comprehension and question answering, where all questions are sampled from real anonymized user queries and context passages from which answers in the dataset are derived from real web documents using the most advanced version of the Bing search engine.
WikiQA: A Challenge Dataset for Open-Domain Question Answering
Yi Yang,Wen-tau Yih,Christopher Meek +2 more
- 21 Sep 2015
TL;DR: The WIKIQA dataset is described, a new publicly available set of question and sentence pairs, collected and annotated for research on open-domain question answering, which is more than an order of magnitude larger than the previous dataset.