Bad Company - Neighborhoods in Neural Embedding Spaces Considered Harmful.
COLING(2016)
摘要
We assess the reliability and accuracy of (neural) word embeddings for both modern and historical English and German. Our research provides deeper insights into the empirically justified choice of optimal training methods and parameters. The overall low reliability we observe, nevertheless, casts doubt on the suitability of word neighborhoods in embedding spaces as a basis for qualitative conclusions on synchronic and diachronic lexico-semantic matters, an issue currently high up in the agenda of Digital Humanities.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络