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 1604.01692cs.CL
收藏

一种生成高质量词嵌入的嵌入方法(2016)

An Ensemble Method to Produce High-Quality Word Embeddings (2016)

Luminoso Technologies, Inc.(Luminoso科技公司);Union College(联合学院)

Robyn Speer, Joshua Chin

摘要:

目前成功的计算语义方法是将单词表示为机器学习向量空间中的嵌入。我们提出了一种集成方法,该方法结合了GloVe(Pennington等人,2014)和word2vec(Mikolov等人,2013)与来自语义网络ConceptNet(Speer和Havasi,2012)和PPDB(Ganitkevitch等人,2013年),将他们的信息合并到一个大型的多语言词汇表中。它产生的嵌入在许多单词相似性评估上达到了最先进的性能。其在稀有词评估上的分数为$ρ= .596$(Luong等人,2013年)比以前最知名的系统高出16%。

英文摘要:

A currently successful approach to computational semantics is to represent words as embeddings in a machine-learned vector space. We present an ensemble method that combines embeddings produced by GloVe (Pennington et al., 2014) and word2vec (Mikolov et al., 2013) with structured knowledge from the semantic networks ConceptNet (Speer and Havasi, 2012) and PPDB (Ganitkevitch et al., 2013), merging their information into a common representation with a large, multilingual vocabulary. The embeddings it produces achieve state-of-the-art performance on many word-similarity evaluations. Its score of $ρ= .596$ on an evaluation of rare words (Luong et al., 2013) is 16% higher than the previous best known system.

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。

↑