Unsupervised Neural Categorization for Scientific Publications

Li, Keqian; Zha, Hanwen; Su, Yu; Yan, Xifeng

doi:10.1137/1.9781611975321.5

Cited by 15 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research on concept learning [19,20] focuses on obtaining and exploiting semantically meaningful information from noisy structured data under set expansion [21] or hierarchical clustering [22,23] paradigm, or from unstructured text data [24][25][26][27] by leveraging distributed semantics [28,29]. We build on top of previous work [1] and leverage the shared representation between concepts and tasks to improve downstream applications.…”

Section: Concept Learningmentioning

confidence: 99%

MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learning

Li¹,

Hu²,

Palanisamy³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Accurate understanding of users in terms of predicative segments play an essential role in the day to day operation of modern internet enterprises. Nevertheless, there are significant challenges that limit the quality of data, especially on long tail predictive tasks. In this work, we present MetaCon, our unified predicative segments system with scalable, trillion concepts meta learning that addresses these challenges. It builds on top of a flat concept representation [1] that summarizes entities' heterogeneous digital footprint, jointly considers the entire spectrum of predicative tasks as a single learning task, and leverages principled meta learning approach with efficient first order meta-optimization procedure under a provable performance guarantee in order to solve the learning task. Experiments on both proprietary production datasets and public structured learning tasks demonstrate that MetaCon can lead to substantial improvements over state of the art recommendation and ranking approaches.

show abstract

Section: Concept Learningmentioning

confidence: 99%

MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learning

Li¹,

Hu²,

Palanisamy³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The final document class is assigned based on the vector similarity between labels and documents. • UNEC [15]: this method takes label surface name as its weak supervision. It categorizes documents by learning the semantics and category attribution of concepts inside the corpus.…”

Section: Baselinesmentioning

confidence: 99%

Weakly-Supervised Neural Text Classification

Shen

Zhang

et al. 2018

Proceedings of the 27th ACM International Conference on Information and Knowledge Management

155

162

View full text Add to dashboard Cite

Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification models suffer from the lack of training data in many real-world applications. Although many semisupervised and weakly-supervised text classification models exist, they cannot be easily applied to deep neural models and meanwhile support limited supervision types. In this paper, we propose a weakly-supervised method that addresses the lack of training data in neural text classification. Our method consists of two modules:(1) a pseudo-document generator that leverages seed information to generate pseudo-labeled documents for model pre-training, and (2) a self-training module that bootstraps on real unlabeled data for model refinement. Our method has the flexibility to handle different types of weak supervision and can be easily integrated into existing deep neural models for text classification. We have performed extensive experiments on three real-world datasets from different domains. The results demonstrate that our proposed method achieves inspiring performance without requiring excessive training data and outperforms baseline methods significantly 1 .

show abstract

“…Weak supervision has been studied for building document classifiers in various of forms, including hundreds of labeled training documents (Tang et al, 2015;Miyato et al, 2016;Xu et al, 2017), class/category names (Song and Roth, 2014;Tao et al, 2015;Li et al, 2018), and user-provided seed words Tao et al, 2015). In this paper, we focus on user-provided seed words as the source of weak supervision, Along this line, Doc2Cube (Tao et al, 2015) expands label keywords from label surface names and performs multidimensional document classification by learning dimension-aware embedding; PTE (Tang et al, 2015) utilizes both labeled and unlabeled documents to learn text embeddings specifically for a task, which are later fed to logistic regression classifiers for classification; leverage seed information to generate pseudo documents and introduces a self-training module that bootstraps on real unlabeled data for model refining.…”

Section: Weak Supervision For Text Classificationmentioning

confidence: 99%

Contextualized Weak Supervision for Text Classification

Mekala¹,

Shang²

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Weakly supervised text classification based on a few user-provided seed words has recently attracted much attention from researchers. Existing methods mainly generate pseudo-labels in a context-free manner (e.g., string matching), therefore, the ambiguous, context-dependent nature of human language has been long overlooked. In this paper, we propose a novel framework ConWea, providing contextualized weak supervision for text classification. Specifically, we leverage contextualized representations of word occurrences and seed word information to automatically differentiate multiple interpretations of the same word, and thus create a contextualized corpus. This contextualized corpus is further utilized to train the classifier and expand seed words in an iterative manner. This process not only adds new contextualized, highly label-indicative keywords but also disambiguates initial seed words, making our weak supervision fully contextualized. Extensive experiments and case studies on real-world datasets demonstrate the necessity and significant advantages of using contextualized weak supervision, especially when the class labels are fine-grained.

show abstract

Unsupervised Neural Categorization for Scientific Publications

Cited by 15 publications

References 0 publications

MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learning

MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learning

Weakly-Supervised Neural Text Classification

Contextualized Weak Supervision for Text Classification

Contact Info

Product

Resources

About