arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1703.08068cs.CL
收藏

用于语言建模的顺序循环神经网络

Sequential Recurrent Neural Networks for Language Modeling

Saarland University(萨尔大学)

Youssef Oualil, Clayton Greenberg, Mittul Singh, Dietrich Klakow

摘要:

基于前馈神经网络(FNN)的语言模型基于最后N个单词的历史来估计下一个单词的概率,而循环神经网络(RNN)仅基于最后一个单词和在网络中循环的一些上下文信息来执行相同的任务。本文提出了一种新的方法,这两类网络之间的桥梁的差距。特别是,我们提出了一种架构,它利用了明确的,顺序枚举的FNN结构中的单词历史,同时通过在网络中不断演变的经常性上下文信息,增强每个单词在投影层的表示。使用也在训练期间学习的附加词相关权重矩阵来执行上下文整合。在Penn Treebank(PTB)和Large Text Compression Benchmark(LTCB)语料库上进行的大量实验表明,与最先进的前馈和递归神经网络架构相比,该算法的困惑度显著降低。

英文摘要:

Feedforward Neural Network (FNN)-based language models estimate the probability of the next word based on the history of the last N words, whereas Recurrent Neural Networks (RNN) perform the same task based only on the last word and some context information that cycles in the network. This paper presents a novel approach, which bridges the gap between these two categories of networks. In particular, we propose an architecture which takes advantage of the explicit, sequential enumeration of the word history in FNN structure while enhancing each word representation at the projection layer through recurrent context information that evolves in the network. The context integration is performed using an additional word-dependent weight matrix that is also learned during the training. Extensive experiments conducted on the Penn Treebank (PTB) and the Large Text Compression Benchmark (LTCB) corpus showed a significant reduction of the perplexity when compared to state-of-the-art feedforward as well as recurrent neural network architectures.

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。

↑