Comparison and Fine-Grained Analysis of Sequence Encoders for Natural Language Processing
<p> Most machine learning algorithms require a fixed length input to be able to perform commonly desired tasks such as classification, clustering, and regression. For natural language processing, the inherently unbounded and recursive nature of the input poses a unique challenge when deriving...
Main Author: | |
---|---|
Language: | EN |
Published: |
University of California, San Diego
2017
|
Subjects: | |
Online Access: | http://pqdtopen.proquest.com/#viewpdf?dispub=10599339 |