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 1702.07680cs.CLcs.IRstat.ML
收藏

词嵌入模型的一致对齐

Consistent Alignment of Word Embedding Models

MIT Lincoln Laboratory(麻省理工学院林肯实验室)

Cem Safak Sahin, Rajmonda S. Caceres, Brandon Oselio, William M. Campbell

摘要:

词嵌入模型提供了连续的向量表示,可以根据词的共现模式捕获丰富的上下文语义。虽然这些词向量可以提供非常有效的功能,用于许多NLP任务,如聚类相似的单词和推断学习关系,但仍然存在许多挑战和开放的研究问题。在本文中,我们提出了一种解决方案,利用精心生成的合成数据点,在联合低维潜在空间中对齐相同模型(或不同模型)的变化。这种生成过程的灵感来自于这样一种观察,即各种语言关系可以通过嵌入空间中的简单线性运算来捕获。我们证明,我们的方法可以导致实质性的改善,在恢复嵌入的本地社区。

英文摘要:

Word embedding models offer continuous vector representations that can capture rich contextual semantics based on their word co-occurrence patterns. While these word vectors can provide very effective features used in many NLP tasks such as clustering similar words and inferring learning relationships, many challenges and open research questions remain. In this paper, we propose a solution that aligns variations of the same model (or different models) in a joint low-dimensional latent space leveraging carefully generated synthetic data points. This generative process is inspired by the observation that a variety of linguistic relationships is captured by simple linear operations in embedded space. We demonstrate that our approach can lead to substantial improvements in recovering embeddings of local neighborhoods.

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。

↑