تقرير
A Generalized Language Model in Tensor Space
العنوان: | A Generalized Language Model in Tensor Space |
---|---|
المؤلفون: | Zhang, Lipeng, Zhang, Peng, Ma, Xindian, Gu, Shuqin, Su, Zhan, Song, Dawei |
سنة النشر: | 2019 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Machine Learning |
الوصف: | In the literature, tensors have been effectively used for capturing the context information in language models. However, the existing methods usually adopt relatively-low order tensors, which have limited expressive power in modeling language. Developing a higher-order tensor representation is challenging, in terms of deriving an effective solution and showing its generality. In this paper, we propose a language model named Tensor Space Language Model (TSLM), by utilizing tensor networks and tensor decomposition. In TSLM, we build a high-dimensional semantic space constructed by the tensor product of word vectors. Theoretically, we prove that such tensor representation is a generalization of the n-gram language model. We further show that this high-order tensor representation can be decomposed to a recursive calculation of conditional probability for language modeling. The experimental results on Penn Tree Bank (PTB) dataset and WikiText benchmark demonstrate the effectiveness of TSLM. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/1901.11167 |
رقم الأكسشن: | edsarx.1901.11167 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!