Topic Modeling using Topics from Many Domains, Lifelong Learning and Big Data

By Zhiyuan Chen, B. Liu. 2014

194 citations recorded by the source corpus.

Subfields: Natural Language Processing, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Bing Liu
2. Hu Xu
3. B. Liu
4. Zixuan Ke
5. Lei Shu
6. Philip S. Yu
7. Sahisnu Mazumder
8. Shuai Wang

In Meta & Continual Learning

1. Bing Liu
2. Zixuan Ke
3. Hu Xu
4. Lei Shu
5. B. Liu
6. Sahisnu Mazumder
7. Dongyan Zhao
8. Mohammad Rostami

Citations in the corpus

• Adaptive Orthogonal Projection for Batch and Online Continual Learning (2022, background): “Many techniques have been proposed to solve the problem of catastrophic forgetting (CF) in continual learning (CL), which aims to incrementally learn a sequence of tasks (Chen and Liu 2018).”
• Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks (2021, methodology): “There are also existing methods for knowledge transfer (Ruvolo and Eaton, 2013; Chen and Liu, 2014; Chen et al., 2015; Wang et al., 2019; Ke et al., 2020) when all tasks are similar.”
• Continual Learning by Using Information of Each Class Holistically (2021, background): “Traditional lifelong learning methods are also related (Ruvolo and Eaton 2013; Chen and Liu 2014; Benavides-Prado, Koh, and Riddle 2020).”
• Lifelong and Continual Learning Dialogue Systems: Learning during Conversation (2021, methodology): “The first part of the definition is taken from (Chen and Liu 2018) based on the early work in (Thrun 1998; Silver, Yang, and Li 2013; Ruvolo and Eaton 2013; Chen and Liu 2014) and the second part of on-the-job learning is proposed in (Liu 2020).”
• Lifelong Learning for Sentiment Classification (2015, background): “Existing lifelong learning approaches focused on exploiting invariances (Thrun, 1998) and other types of knowledge (Chen and Liu, 2014b, Chen and Liu, 2014a, Ruvolo and Eaton, 2013) across multiple tasks.”
• Continual Learning with Knowledge Transfer for Sentiment Classification (2021, background): “Lifelong learning is also closely related [27, 22, 3, 4], which mainly aims to improve the new task learning through”
• Learning on the Job: Online Lifelong and Continual Learning (2020, background): “but limited work has been done in (Chen and Liu, 2014; Mitchell et al., 2015; Bou Ammar et al, 2015).”
• Lifelong Learning CRF for Supervised Aspect Extraction (2017, background): “The second type has 50 unlabeled review datasets from 50 domains or types of products (Chen and Liu, 2014).”
• CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks (2021, background): “Early works are done under Lifelong Learning (LL) (Silver et al., 2013; Ruvolo and Eaton, 2013; Chen and Liu, 2014).”
• Forward and Backward Knowledge Transfer for Sentiment Classification (2019, methodology): “Following the work in Chen et al. (2015), we treat the classification in each domain (e.”
• Lifelong Learning Memory Networks for Aspect Sentiment Classification (2018, methodology): “Our work is also related to lifelong machine learning (LML) [12], [24], [25].”
• Machine Learning With Big Data: Challenges and Approaches (2017, background): “Chen and Liu [119] suggested an unsupervised learning algorithm, the Gibbs Sampler, for mining the topic model and for generating a better knowledge space in the context of e-commerce reviews.”
• Using the Past Knowledge to Improve Sentiment Classification (2020, background): “Lifelong learning : Most relevant to our work is lifelong learning (Thrun, 1998; Silver et al., 2013; Ruvolo and Eaton, 2013; Chen and Liu, 2014, 2016).”
• Lifelong Learning Dialogue Systems: Chatbots that Self-Learn On the Job (2020, methodology): “The proposed LINC paradigm is based on the traditional lifelong learning (LL) (Chen and Liu 2018; Thrun 1998; Silver, Yang, and Li 2013; Ruvolo and Eaton 2013; Chen and Liu 2014), but also needs significant extensions.”
• Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition (2017, background): “Recent work in lifelong machine learning [9, 27, 29] has explored the notion of a single agent accumulating knowledge over its lifetime.”