按年被提到
20172017 · 1 次2026
大模型与语言模型›大模型评测与真实性·arXiv:1704.05179 · cs.CL

SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine

Matthew Dunn, Levent Sagun, Mike Higgins, V. Ugur Guney, Volkan Cirik, Kyunghyun Cho · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-04-19 · 最近 2019-02-28
2不同的人
2活跃月份
2讨论串
357被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We publicly release a new large-scale dataset, called SearchQA, for machine comprehension, or question-answering. Unlike recently released datasets, such as DeepMind CNN/DailyMail and SQuAD, the proposed SearchQA was constructed to reflect a full pipeline of general question-answering. That is, we start not from an existing article and generate a question-answer pair, but start from an existing question-answer pair, crawled from J! Archive, and augment it with text snippets retrieved by Google. Following this approach, we built SearchQA, which consists of more than 140k question-answer pairs with each pair having 49.6 snippets on average. Each question-answer-context tuple of the SearchQA comes with additional meta-data such as the snippet's URL, which we believe will be valuable resources for future research. We conduct human evaluation as well as test two baseline methods, one simple word selection and the other deep learning based, on the SearchQA. We show that there is a meaningful gap between the human and machine performances. This suggests that the proposed dataset could well serve as a benchmark for question-answering.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论andreyk · 2019-02

“Some other fun recent-ish developments in QA datasets: - Natural Questions (https://ai.googleblog.com/2019/01/natural-questions-new-corpus-and.html) - SearchQA (https://arxiv.org/abs/1704.05179) Many AI researchers worry the community is overfitting to getting good numbers and not thinking big enough, but it seems to me datasets evolve fast enough to k…”

Beyond Local Pattern Matching: Recent Advances in Machine Reading原评论 ↗
被提交为 story · 1 次