首页> 外文会议>3rd workshop on representation learning for NLP 2018 >Extrofitting: Enriching Word Representation and its Vector Space with Semantic Lexicons
【24h】

Extrofitting: Enriching Word Representation and its Vector Space with Semantic Lexicons

机译:扩展:利用语义词典丰富单词表示及其向量空间

获取原文
获取原文并翻译 | 示例

摘要

We propose post-processing method for enriching not only word representation but also its vector space using semantic lexicons, which we call extrofitting. The method consists of 3 steps as follows: (ⅰ) Expanding 1 or more dimension(s) on all the word vectors, filling with their representative value, (ⅱ) Transferring semantic knowledge by averaging each representative values of synonyms and filling them in the expanded dimension(s). These two steps make representations of the synonyms close together, (ⅲ) Projecting the vector space using Linear Discriminant Analysis, which eliminates the expanded dimension(s) with semantic knowledge. When experimenting with GloVe, we find that our method outperforms Faruqui's retrofitting on some of word similarity task. We also report further analysis on our method in respect to word vector dimensions, vocabulary size as well as other well-known pretrained word vectors (e.g., Word2Vec, Fasttext).
机译:我们提出了一种后处理方法,不仅可以利用语义词典来丰富单词表示,而且可以丰富其向量空间,我们称其为外加。该方法包括以下3个步骤:(ⅰ)在所有单词向量上扩展1个或多个维度,填充其代表值,(ⅱ)通过平均同义词的每个代表值并将其填充到词中来传递语义知识扩展尺寸。这两个步骤使同义词的表示接近在一起,(ⅲ)使用线性判别分析投影向量空间,从而消除了具有语义知识的扩展维。在使用GloVe进行实验时,我们发现我们的方法在某些单词相似性任务上胜过Faruqui的改进。我们还报告了关于我们的方法的进一步分析,包括词向量维数,词汇量以及其他众所周知的预训练词向量(例如Word2Vec,Fasttext)。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号