Take and Took，Gaggle and Goose，Book and Read：Evaluating the Utility of Vector Differences for Lexical Relation Learning（英语：Vector-differences）
Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning
摘要：
最近关于词嵌入的工作表明，在预先训练的嵌入上进行简单的向量减法在捕获不同的词汇关系方面是惊人的有效，尽管缺乏明确的监督。先前的工作已经评估了这个有趣的结果，使用一个词的类比预测公式和手工选择的关系，但在更广泛的词汇关系类型和不同的学习设置的发现的一般性还没有得到评估。在本文中，我们进行了这样的评估，在两个学习设置：（1）谱聚类诱导词的关系，和（2）监督学习分类向量差异到关系类型。我们发现，词嵌入捕获了惊人的信息量，并且在适当的监督训练下，向量减法可以很好地推广到广泛的关系，包括看不见的词汇项。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
