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 1704.01419cs.CL
收藏

词嵌入模型的线性集成

Linear Ensembles of Word Embedding Models

University of Tartu(塔尔图大学)

Avo Muromägi, Kairit Sirts, Sven Laur

摘要:

本文探讨了线性方法结合成一个整体的几个词嵌入模型。我们使用基于普通最小二乘回归或正交Procrustes问题的解决方案的迭代法构建组合模型。我们评估爱沙尼亚语-一种形态复杂的语言,可用的语料库训练词嵌入是相对较小的建议的方法。我们比较两个组合模型彼此之间,并与输入词嵌入模型使用同义词和类比测试。实验结果表明,普通最小二乘回归方法在实验中表现不佳,而正交Procrustes方法将多个词嵌入模型组合成一个集成模型,在同义词测试中比初始模型的平均结果相对提高了7-10%,在类比测试中比初始模型的平均结果相对提高了19-47%。

英文摘要:

This paper explores linear methods for combining several word embedding models into an ensemble. We construct the combined models using an iterative method based on either ordinary least squares regression or the solution to the orthogonal Procrustes problem. We evaluate the proposed approaches on Estonian---a morphologically complex language, for which the available corpora for training word embeddings are relatively small. We compare both combined models with each other and with the input word embedding models using synonym and analogy tests. The results show that while using the ordinary least squares regression performs poorly in our experiments, using orthogonal Procrustes to combine several word embedding models into an ensemble model leads to 7-10% relative improvements over the mean result of the initial models in synonym tests and 19-47% in analogy tests.

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。

↑