按年被提到
20182018 · 2 次2026
大模型与语言模型›大模型评测与真实性·arXiv:1806.02847 · cs.AI

A Simple Method for Commonsense Reasoning

Trieu H. Trinh, Quoc V. Le · 2018
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2018-06-12 · 最近 2018-11-07
2不同的人
2活跃月份
2讨论串
293被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Commonsense reasoning is a long-standing challenge for deep learning. For example, it is difficult to use neural networks to tackle the Winograd Schema dataset (Levesque et al., 2011). In this paper, we present a simple method for commonsense reasoning with neural networks, using unsupervised learning. Key to our method is the use of language models, trained on a massive amount of unlabled data, to score multiple choice questions posed by commonsense reasoning tests. On both Pronoun Disambiguation and Winograd Schema challenges, our models outperform previous state-of-the-art methods by a large margin, without using expensive annotated knowledge bases or hand-engineered features. We train an array of large RNN language models that operate at word or character level on LM-1-Billion, CommonCrawl, SQuAD, Gutenberg Books, and a customized corpus for this task and show that diversity of training data plays an important role in test performance. Further analysis also shows that our system successfully discovers important features of the context that decide the correct answer, indicating a good grasp of commonsense knowledge.

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nl · 2018-06

“Also notable this week is https://arxiv.org/abs/1806.02847 from Google where they got an 11% improvement on Winograd schema performance using a similar idea.”

Improving Language Understanding with Unsupervised Learning原评论 ↗
评论glup · 2018-11

“bert provides incremental improvements on tasks that don't really stress-test contextualized world knowledge in linguistic tasks — contrast with Winograd schemas (SOTA: https://arxiv.org/pdf/1806.02847.pdf). Corpus data and compute don't magically solve everything.”

Artificial Intelligence Hits the Barrier of Meaning原评论 ↗