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 1707.01555cs.CLcs.AIcs.NE
收藏

一个具有可视文本合成行为的深度网络

A Deep Network with Visual Text Composition Behavior

National Research Council Canada(加拿大国家研究委员会)

Hongyu Guo

摘要:

虽然自然语言是组合的,但最先进的神经模型如何实现组合性仍不清楚。我们提出了一个深度网络,它不仅可以实现具有竞争力的文本分类准确性,而且还表现出组合行为。也就是说,在创建一段文本(如句子)的分层表示时,网络的较低层将其特定于层的注意力权重分配给各个单词。相比之下,更高的层次组成有意义的短语和从句,其长度随着网络的加深而增加,直到完全组成句子。

英文摘要:

While natural languages are compositional, how state-of-the-art neural models achieve compositionality is still unclear. We propose a deep network, which not only achieves competitive accuracy for text classification, but also exhibits compositional behavior. That is, while creating hierarchical representations of a piece of text, such as a sentence, the lower layers of the network distribute their layer-specific attention weights to individual words. In contrast, the higher layers compose meaningful phrases and clauses, whose lengths increase as the networks get deeper until fully composing the sentence.

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。

↑