Disentangling Aspect and Opinion Words in Sentiment Analysis Using Lifelong PU Learning

Wang, Shuai; Zhou, Mianwei; Mazumder, Sahisnu; Liu, Bing; Chang, Yi

doi:10.1007/978-3-030-48861-1_7

Cited by 1 publication

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A novel lifelong framework for sentiment classification was proposed by Chen et al (2015) using optimization approach based on the naive Bayesian framework and stochastic gradient descent algorithm. Wang, Zhou, et al (2018) used the idea of lifelong learning to overcome the inefficiencies of error propagation in PU learning, which is a semi‐supervised learning wherein ‘P’ signifies positive sentiments, and ‘U’ is unlabeled data. The aim is to build a binary classifier that extracts positive sentiments from unlabeled data.…”

Section: Lifelong Machine Learningmentioning

confidence: 99%

The role of lifelong machine learning in bridging the gap between human and machine learning: A scientometric analysis

Abulaish,

Wasi,

Sharma

2024

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Due to advancements in data collection, storage, and processing techniques, machine learning has become a thriving and dominant paradigm. However, one of its main shortcomings is that the classical machine learning paradigm acts in isolation without utilizing the knowledge gained through learning from related tasks in the past. To circumvent this, the concept of Lifelong Machine Learning (LML) has been proposed, with the goal of mimicking how humans learn and acquire cognition. Human learning research has revealed that the brain connects previously learned information while learning new information from a single or small number of examples. Similarly, an LML system continually learns by storing and applying acquired information. Starting with an analysis of how the human brain learns, this paper shows that the LML framework shares a functional structure with the brain when it comes to solving new problems using previously learned information. It also provides a description of the LML framework, emphasizing its similarities to human brain learning. It also provides citation graph generation and scientometric analysis algorithms for the LML literatures, including information about the datasets and evaluation metrics that have been used in the empirical evaluation of LML systems. Finally, it presents outstanding issues and possible future research directions in the field of LML.This article is categorized under: Technologies > Machine Learning

show abstract

Section: Lifelong Machine Learningmentioning

confidence: 99%