arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1607.02802cs.CLcs.AIstat.ML
收藏

从分布语义空间到模型论语义空间的映射:一个基线

Mapping distributional to model-theoretic semantic spaces: a baseline

MIT(麻省理工学院)

Franck Dernoncourt

摘要:

在许多自然语言处理任务中,词嵌入已被证明在最先进的系统中是有用的,范围从问答系统到依存句法分析。(Herbelot和Vecchi,2015)探索了词嵌入及其在建模语言语义中的实用性。特别是,他们提出了一种使用偏最小二乘回归将标准分布语义空间自动映射到集合理论模型的方法。我们在本文中表明,与他们使用的两个数据集之一的模型相比,一个简单的基线实现了+51%的相对改进,并在第二个数据集上产生了有竞争力的结果。

英文摘要:

Word embeddings have been shown to be useful across state-of-the-art systems in many natural language processing tasks, ranging from question answering systems to dependency parsing. (Herbelot and Vecchi, 2015) explored word embeddings and their utility for modeling language semantics. In particular, they presented an approach to automatically map a standard distributional semantic space onto a set-theoretic model using partial least squares regression. We show in this paper that a simple baseline achieves a +51% relative improvement compared to their model on one of the two datasets they used, and yields competitive results on the second dataset.

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。

↑