arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.05907cs.CL
收藏

Syntree2Vec -一种将句法层次增加到词嵌入中的算法

Syntree2Vec - An algorithm to augment syntactic hierarchy into word embeddings

VIT, Vellore(韦洛尔理工学院)

Shubham Bhardwaj

摘要:

词嵌入的目的是将词的意义映射到一个较低维的向量空间,以便对它们进行推理。在领域特定数据上训练嵌入有助于表达与其用例更相关的概念,但当数据较少时,准确性会降低。我们的努力是通过将语法知识注入嵌入来最大限度地减少这一点。我们提出了一个基于图的嵌入算法的灵感来自node 2 vec。实验结果表明,我们的算法提高了语法强度,并给出了少量数据的鲁棒性能。

英文摘要:

Word embeddings aims to map sense of the words into a lower dimensional vector space in order to reason over them. Training embeddings on domain specific data helps express concepts more relevant to their use case but comes at a cost of accuracy when data is less. Our effort is to minimise this by infusing syntactic knowledge into the embeddings. We propose a graph based embedding algorithm inspired from node2vec. Experimental results have shown that our algorithm improves the syntactic strength and gives robust performance on meagre data.

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。

↑