按年被提到
20152015 · 1 次2026
大模型与语言模型›词向量与预训练模型·arXiv:1509.01692 · cs.CL

Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning

Ekaterina Vylomova, Laura Rimell, Trevor Cohn, Timothy Baldwin · 2015
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2015-09-23 · 最近 2023-12-15
2不同的人
2活跃月份
2讨论串
138被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Recent work on word embeddings has shown that simple vector subtraction over pre-trained embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision. Prior work has evaluated this intriguing result using a word analogy prediction formulation and hand-selected relations, but the generality of the finding over a broader range of lexical relation types and different learning settings has not been evaluated. In this paper, we carry out such an evaluation in two learning settings: (1) spectral clustering to induce word relations, and (2) supervised learning to classify vector differences into relation types. We find that word embeddings capture a surprising amount of information, and that, under suitable supervised training, vector subtraction generalises well to a broad range of relations, including over unseen lexical items.

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pjs_ · 2023-12

“Perhaps I'm missing something but this looks like a heavy case of what's old is new again - the original "king - man + woman = queen" paper is nearly a decade old: https://arxiv.org/abs/1509.01692”

Embeddings, Vectors, and Arithmetic原评论 ↗
被提交为 story · 1 次