Combining Discrete Wavelet and Cosine Transforms for Efficient Sentence Embedding скачать в хорошем качестве

Combining Discrete Wavelet and Cosine Transforms for Efficient Sentence Embedding

Combining Discrete Wavelet and Cosine Transforms for Efficient Sentence Embedding Rana Salama1,3, Abdou Youssef1 and Mona Diab2, 1George Washington University, USA, 2Carnegie Mellon University, USA, 3Cairo University, USA Abstract Wavelets have emerged as a cutting edge technology in a number of fields. Concrete results of their application in Image and Signal processing suggest that wavelets can be effectively applied to Natural Language Processing (NLP) tasks that capture a variety of linguistic properties. In this paper, we leverage the power of applying Discrete Wavelet Transforms (DWT) to word and sentence embeddings. We first evaluate, intrinsically and extrinsically, how wavelets can effectively be used to consolidate important information in a word vector while reducing its dimensionality. We further combine DWT with Discrete Cosine Transform (DCT) to propose a non-parameterized model that compresses a sentence with a dense amount of information in a fixed size vector based on locally varying word features. We show the efficacy of the proposed paradigm on downstream applications models yielding comparable and even superior (in some tasks) results to original embeddings. Keywords Word Embedding, Sentence Embedding, Discrete Wavelets Transform, Discrete Cosine Transform Full Text : https://aircconline.com/csit/papers/v... Abstract URL : https://aircconline.com/csit/abstract... Volume URL : https://airccse.org/csit/V14N10.html #naturallanguageprocessing #detection #linguistics #semantics