Bilingual Lexical Induction (BLI) is a core challenge in NLP, it relies on
the relative isomorphism of individual embedding spaces. Existing attempts
aimed at controlling the relative isomorphism of different embedding spaces
fail to incorporate the impact of semantically related words in the model
training objective. To address this, we propose GARI that combines the
distributional training objectives with multiple isomorphism losses guided by
the graph attention network. GARI considers the impact of semantical variations
of words in order to define the relative isomorphism of the embedding spaces.
Experimental evaluation using the Arabic language data set shows that GARI
outperforms the existing research by improving the average P@1 by a relative
score of up to 40.95% and 76.80% for in-domain and domain mismatch settings
respectively. We release the codes for GARI at
this https URL

在 NLP 中，双语词汇归纳（BLI）是一个核心挑战，它依赖于个体嵌入空间的相对同构性。我们提出了 GARI，它将分布式训练目标与由图形注意网络指导的多个同构损失相结合，以控制不同嵌入空间的相对同构性，并考虑了单词的语义变化影响以定义嵌入空间的相对同构性，实验结果表明 GARI 在阿拉伯语言数据集上的表现优于现有研究，平均 P@1 在领域内和领域不匹配设置下的相对得分分别提高了 40.95% 和 76.80%。我们在此 https URL 放出了 GARI 的代码。