arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.04863cs.CL
收藏

分布式词嵌入的无监督对齐

Unsupervised Alignment of Distributional Word Embeddings

University College London(伦敦大学学院);Johannes Kepler University Linz(林茨约翰内斯·开普勒大学)

Aissatou Diallo, Johannes Fürnkranz

摘要:

跨领域对齐在从机器翻译到迁移学习的各种任务中起着关键作用。最近,纯无监督的方法操作单语嵌入已成功地用于推断双语词典,而不依赖于监督。然而,目前的最先进的方法只关注点向量,虽然分布式嵌入已被证明嵌入更丰富的语义信息时,表示的话。在本文中,我们提出了随机优化方法对齐概率嵌入。最后,我们通过对齐在单语数据上训练的词嵌入来评估我们在无监督词翻译问题上的方法。我们表明,所提出的方法在双语词典归纳任务上取得了良好的性能,在几种语言对,并表现得比基于点向量的方法。

英文摘要:

Cross-domain alignment play a key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have successfully been used to infer a bilingual lexicon without relying on supervision. However, current state-of-the art methods only focus on point vectors although distributional embeddings have proven to embed richer semantic information when representing words. In this paper, we propose stochastic optimization approach for aligning probabilistic embeddings. Finally, we evaluate our method on the problem of unsupervised word translation, by aligning word embeddings trained on monolingual data. We show that the proposed approach achieves good performance on the bilingual lexicon induction task across several language pairs and performs better than the point-vector based approach.

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。

↑