按年被提到
20192019 · 3 次2026
大模型与语言模型›词向量与预训练模型·arXiv:1906.04341 · cs.CL

What Does BERT Look At? An Analysis of BERT's Attention

Kevin Clark, Urvashi Khandelwal, Omer Levy, Christopher D. Manning · 2019
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 4 人首次 2019-06-12 · 最近 2023-02-17
4不同的人
2活跃月份
4讨论串
1,512被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large pre-trained neural networks such as BERT have had great recent success in NLP, motivating a growing body of research investigating what aspects of language they are able to learn from unlabeled data. Most recent analysis has focused on model outputs (e.g., language model surprisal) or internal vector representations (e.g., probing classifiers). Complementary to these works, we propose methods for analyzing the attention mechanisms of pre-trained models and apply them to BERT. BERT's attention heads exhibit patterns such as attending to delimiter tokens, specific positional offsets, or broadly attending over the whole sentence, with heads in the same layer often exhibiting similar behaviors. We further show that certain attention heads correspond well to linguistic notions of syntax and coreference. For example, we find heads that attend to the direct objects of verbs, determiners of nouns, objects of prepositions, and coreferent mentions with remarkably high accuracy. Lastly, we propose an attention-based probing classifier and use it to further demonstrate that substantial syntactic information is captured in BERT's attention.

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KhoomeiK · 2023-02

“Several papers have explored emergent linguistic structure in LMs. Here's some early introductory work in this space. Despite having explicit syntax parses etc as input, models seem to learn something like syntax. https://arxiv.org/abs/1905.05950 https://aclanthology.org/N19-1419/ https://arxiv.org/abs/1906.04341”

We Found an Neuron in GPT-2原评论 ↗
被提交为 story · 3 次