Lifelong Learning CRF for Supervised Aspect Extraction

By Lei Shu, Hu Xu, B. Liu. 2017

105 citations recorded by the source corpus.

This paper makes a focused contribution to supervised aspect extraction. It shows that if the system has performed aspect extraction from many past domains and retained their results as knowledge, Conditional Random Fields (CRF) can leverage this knowledge in a lifelong learning manner to extract in a new domain markedly better than the traditional CRF without using this prior knowledge. The key innovation is that even after CRF training, the model can still improve its extraction with experiences in its applications.

Subfields: Artificial Intelligence, Information Systems, 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 Artificial Intelligence

In Information Systems

In Natural Language Processing

In Meta & Continual Learning

Citations in the corpus

Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning (2021, neutral): “[55] used LL for aspect extraction.”
Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks (2021, methodology): “Shu et al. (2017) used LL for aspect extraction, which is a different problem.”
Continual Lifelong Learning in Natural Language Processing: A Survey (2020, methodology): “Furthermore, Shu et al. (2017) proposed a method based on conditional random fields to improve supervised aspect extraction across time.”
DOC: Deep Open Classification of Text Documents (2017, methodology): “We also plan to improve model performance during testing (Shu et al., 2017).”
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.”
Continual Learning with Knowledge Transfer for Sentiment Classification (2021, methodology): “The work in [26, 29] uses LL for aspect-based sentiment analysis, which is an entirely different problem than document-level sentiment classification (SC) studied in this paper.”
Learning on the Job: Online Lifelong and Continual Learning (2020, background): “Steps 1 and 3 have been studied in open-world learning (Shu et al., 2017a, 2018; Chen and Liu, 2018) and continual learning (Chen and Liu, 2018; Parisi et al., 2018) respectively.”
CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks (2021, neutral): “Shu et al. (2017) used LL for aspect extraction.”
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).”
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.”
Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction (2018, methodology): “Aspect extraction has been performed using supervised (Jakob and Gurevych, 2010; Chernyshe-vich, 2014; Shu et al., 2017) and unsupervised approaches (Hu and Liu, 2004; Zhuang et al., 2006; Mei et al., 2007; Qiu et al., 2011; Yin et al., 2016; He et al., 2017).”
Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research (2020, methodology): “traction include rule-based strategies (Qiu et al., 2011; Liu et al., 2015), topic models (Mei et al., 2007; He et al., 2011), and more recently, sequential structured-prediction models such as CRFs (Shu et al., 2017). For aspect-level sentiment analysis, the algorithms primarily aim to model the re”
Towards a Continuous Knowledge Learning Engine for Chatbots (2018, background): “Our work is related to general lifelong learning in (Chen and Liu, 2016; Ruvolo and Eaton, 2013; Chen and Liu, 2014, 2013; Bou Ammar et al., 2015; Shu et al., 2017).”
DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification (2018, background): “Training a deep learning classiﬁer on small datasets is a topic of wide interests in the ﬁelds of ﬁne-grained visual recognition [15], few-shot learning [16], and life-long learning in new environments [17].”