Lifelong-RL: Lifelong Relaxation Labeling for Separating Entities and Aspects in Opinion Targets

By Lei Shu, B. Liu, Hu Xu, Annice Kim. 2016

34 citations recorded by the source corpus.

It is well-known that opinions have targets. Extracting such targets is an important problem of opinion mining because without knowing the target of an opinion, the opinion is of limited use. So far many algorithms have been proposed to extract opinion targets. However, an opinion target can be an entity or an aspect (part or attribute) of an entity. An opinion about an entity is an opinion about the entity as a whole, while an opinion about an aspect is just an opinion about that specific attribute or aspect of an entity. Thus, opinion targets should be separated into entities and aspects before use because they represent very different things about opinions. This paper proposes a novel algorithm, called Lifelong-RL, to solve the problem based on lifelong machine learning and relaxation labeling. Extensive experiments show that the proposed algorithm Lifelong-RL outperforms baseline methods markedly.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

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

In Artificial Intelligence

1. Bing Liu
2. Hu Xu
3. Lei Shu
4. Caiming Xiong
5. Richard Socher
6. Philip S. Yu
7. B. Liu
8. Pascale Fung

In Information Systems

1. B. Liu
2. Bing Liu
3. Hu Xu
4. Lei Shu
5. Geli Fei
6. Philip S. Yu
7. Shuai Wang
8. Marta Ruiz Costa-jussà

Citations in the corpus

• Continual Lifelong Learning in Natural Language Processing: A Survey (2020, methodology): “Shu et al. (2016) presented an unsupervised CL approach to classify opinion targets into entities and aspects.”
• Sentence Embedding Alignment for Lifelong Relation Extraction (2019, background): “Remark It is worth noting that the term life-long learning is also widely used in (Chen et al., 2015; Chen, 2015; Shu et al., 2016, 2017), which mainly focus on how to represent, reserve and extract knowledge of previous tasks.”
• Lifelong Learning CRF for Supervised Aspect Extraction (2017, background): “, 2013), label propagation (Zhou et al., 2013; Shu et al., 2016), and others (Zhao et al.”
• Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems (2019, background): “The applications within NLP has been comparatively limited, e.g., Shu et al. (2016, 2017b) for opinion mining, Shu et al. (2017a) for document classification, and Lee (2017) for hybrid code networks (Williams et al., 2017).”
• Lifelong Learning Memory Networks for Aspect Sentiment Classification (2018, methodology): “Our experimental setup follows prior research about lifelong learning [13], [24], [29].”
• Lifelong Domain Word Embedding via Meta-Learning (2018, background): “In recent years, several LL works have also been done for unsupervised learning, e.g., topic modeling [Chen and Liu, 2014], information extraction [Mitchell et al. , 2018] and graph labeling [Shu et al. , 2016].”
• Deep Bayesian Unsupervised Lifelong Learning (2021, result): “This is in contrast to existing work which uses previous model parameters [5, 20], representative items exacted from previous models [21] or past raw data, or coreset data summarization [16, 17, 18] as previous knowledge for new tasks.”