基于判别短语嵌入的释义识别
Discriminative Phrase Embedding for Paraphrase Identification
摘要:
这项关于释义识别任务的工作,一方面有助于扩展深度学习嵌入,以包括连续和不连续的语言短语。另一方面,提出了一种新的算法TF-KLD-KNN来学习释义任务中单词和短语的区分权值,使得嵌入的加权和能够更有效地表示句子。基于这两个创新,我们得到了具有竞争力的最先进的性能的释义识别。
英文摘要:
This work, concerning paraphrase identification task, on one hand contributes to expanding deep learning embeddings to include continuous and discontinuous linguistic phrases. On the other hand, it comes up with a new scheme TF-KLD-KNN to learn the discriminative weights of words and phrases specific to paraphrase task, so that a weighted sum of embeddings can represent sentences more effectively. Based on these two innovations we get competitive state-of-the-art performance on paraphrase identification.
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。