arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1301.3226cs.LGcs.CLstat.ML
收藏

词嵌入的表现力

The Expressive Power of Word Embeddings

Yanqing Chen, Bryan Perozzi, Rami Al-Rfou, Steven Skiena

摘要:

我们试图更好地理解几个公开发布的嵌入的质量差异。我们提出了几个任务,有助于区分不同的嵌入的特点。我们对情感极性和同义词/反义词关系的评估表明,即使在没有句子结构的情况下,嵌入也能够捕捉到令人惊讶的细微差别的语义。此外,基准测试的嵌入显示了很大的差异,在质量和测试嵌入捕获的语义特性。最后,我们展示了不同维数和每个维度的分辨率对嵌入空间捕获的有效有用特征的影响。我们的贡献突出了嵌入对于NLP任务的重要性以及它们的质量对最终结果的影响。

英文摘要:

We seek to better understand the difference in quality of the several publicly released embeddings. We propose several tasks that help to distinguish the characteristics of different embeddings. Our evaluation of sentiment polarity and synonym/antonym relations shows that embeddings are able to capture surprisingly nuanced semantics even in the absence of sentence structure. Moreover, benchmarking the embeddings shows great variance in quality and characteristics of the semantics captured by the tested embeddings. Finally, we show the impact of varying the number of dimensions and the resolution of each dimension on the effective useful features captured by the embedding space. Our contributions highlight the importance of embeddings for NLP tasks and the effect of their quality on the final results.

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。

↑