arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1206.6403cs.CLcs.LG
收藏

两步CCA:一种新的词向量模型谱估计方法

Two Step CCA: A new spectral method for estimating vector models of words

University of Pennsylvania(宾夕法尼亚大学);The Wharton School(沃顿商学院)

Paramveer Dhillon, Jordan Rodu, Dean Foster, Lyle Ungar

摘要:

未标记数据通常用于学习表示,这些表示可用于补充监督学习器中的基线特征。例如,对于单词位于非常高维空间(词汇表的大小)中的文本应用,可以通过单词共现矩阵的特征分解(例如,使用PCA或CCA)来学习低秩“字典”。本文提出了一种新的基于CCA的谱方法来学习特征词词典。我们改进的过程计算两组CCA,第一组CCA在给定单词的左右上下文之间,第二组CCA在由CCA产生的投影与单词本身之间。我们从理论上证明了这种两步过程比简单的单步的过程具有更低的样本复杂度,并且还说明了我们的方法的经验有效性和我们的两步CCA(TSCCA)过程在词性标注和情感分类任务上学习到的表征的丰富性。

英文摘要:

Unlabeled data is often used to learn representations which can be used to supplement baseline features in a supervised learner. For example, for text applications where the words lie in a very high dimensional space (the size of the vocabulary), one can learn a low rank "dictionary" by an eigen-decomposition of the word co-occurrence matrix (e.g. using PCA or CCA). In this paper, we present a new spectral method based on CCA to learn an eigenword dictionary. Our improved procedure computes two set of CCAs, the first one between the left and right contexts of the given word and the second one between the projections resulting from this CCA and the word itself. We prove theoretically that this two-step procedure has lower sample complexity than the simple single step procedure and also illustrate the empirical efficacy of our approach and the richness of representations learned by our Two Step CCA (TSCCA) procedure on the tasks of POS tagging and sentiment classification.

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。

↑