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
Contrastive Learning between Classical and Modern Chinese for Classical Chinese Machine Reading Comprehension
Mao-hong Liu,Junyi Xiang,Xu Xia,Huijun Hu +3 more
- 05 Aug 2022
TL;DR: A contrastive learning method between classical and modern Chinese in order to reach a deep understanding of the two different styles and improves language understanding ability and outperforms existing PLMs on the Haihua, CCLUE, and ChID datasets.
2
PAG-LLM: Paraphrase and Aggregate with Large Language Models for Minimizing Intent Classification Errors
Vikas Yadav,Zheng Tang,Vijay Srinivasan +2 more
- 10 Jul 2024
TL;DR: This study introduces PAG-LLM, a method that uses large language models to generate multiple paraphrases of input queries, perform multi-class classification, and aggregate labels based on confidence scores, achieving 22.7% and 15.1% error reduction on two large datasets.
AmbigDocs: Reasoning across Documents on Different Entities under the Same Name
TL;DR: AmbigDocs is a benchmark for testing the ability of LMs to distinguish different entities with the same name. It includes documents and questions designed to test this ability, as well as an ontology and evaluation metrics for measuring incomplete answers.
2
Evaluating Prompt-based Question Answering for Object Prediction in the Open Research Knowledge Graph
Jennifer D'Souza,Sören Auer +1 more
TL;DR: The authors adopted prompt-based training of transformer language models for new text genres in low-resource settings, and found that the models outperformed on a new domain of data, and achieved performance boosts of up to 40% in a relaxed evaluation setting, and testing the models on a starkly different domain even with a clever training objective in a low resource setting.
2
Title2Vec: a contextual job title embedding for occupational named entity recognition and other applications
TL;DR: Li et al. as discussed by the authors presented the Industrial and Professional Occupations Dataset (IPOD), which contains over 475,073 job titles based on 192,295 user profiles from a major professional networking site.
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.