Learning Robust Word Representations for Natural Language Processing

语言是一种高生产力的现象;新的词汇和表达方式不断被发明出来。 目前的自然语言处理技术很难处理新单词，因此它们在真实文本中的性能受到影响。为了解决这个问题，我们开发了强大的单词语义模型，专注于学习矢量单词表示的深度学习方法。此外，我们展示了使用这些单词表示的系统在解析和翻译性能方面的改进。

Language is a highly productive phenomenon; new words and expressions are constantly being invented. Current Natural Language Processing techniques have difficulty handling new words, so their performance on real-world text suffers. To address this, we develop robust models of word semantics, focusing on Deep Learning methods for learning vector word representations. Furthermore, we show improvements in parsing and translation performance using systems that incorporate these word representations.