Text Classification Based on Fuzzy Radial Basis  Function

Ali, Zuhair Hussein

doi:10.25195/ijci.v45i1.40

Cited by 2 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data sparsity and class imbalance are common problems in text classification tasks (Türker et al, 2019;Zhang and Wu, 2015;Shams, 2014;Kumar et al, 2020), especially when the text to be labelled is from a highly-specialised domain where only scarce domain experts can perform the labelling task (Türker et al, 2019;Ali, 2019). Data Augmentation (DA) is a widely used method for tackling such issues (Anaby-Tavor et al, 2020;Kumar et al, 2020;Papanikolaou and Pierleoni, 2019).…”

Section: Introductionmentioning

confidence: 99%

Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification

Edwards¹,

Ushio²,

Camacho-Collados³

et al. 2021

Preprint

View full text Add to dashboard Cite

Data augmentation techniques are widely used for enhancing the performance of machine learning models by tackling class imbalance issues and data sparsity. State-of-the-art generative language models have been shown to provide significant gains across different NLP tasks. However, their applicability to data augmentation for text classification tasks in fewshot settings have not been fully explored, especially for specialised domains. In this paper, we leverage GPT-2 (Radford et al., 2019) for generating artificial training instances in order to improve classification performance. Our aim is to analyse the impact the selection process of seed training examples have over the quality of GPT-generated samples and consequently the classifier performance. We perform experiments with several seed selection strategies that, among others, exploit class hierarchical structures and domain expert selection. Our results show that fine-tuning GPT-2 in a handful of label instances leads to consistent classification improvements and outperform competitive baselines. Finally, we show that guiding this process through domain expert selection can lead to further improvements, which opens up interesting research avenues for combining generative models and active learning.

show abstract

Section: Introductionmentioning

confidence: 99%

Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification

Edwards¹,

Ushio²,

Camacho-Collados³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The performance of natural language processing (NLP) classification tasks is heavily reliant on the amount of training data available (Zhang and Wu, 2015;Türker et al, 2019). However, the acquisition of high volumes of labelled data can be an expensive, time-and resource-consuming process (Ali, 2019), especially when the text to be labelled is in a highly-specialised domain where only scarce domain experts can perform the manual labelling task (Türker et al, 2019). Further, for many domains, the documents available are sparse and hard to obtain.…”

Section: Introductionmentioning

confidence: 99%

Predicting Themes within Complex Unstructured Texts: A Case Study on Safeguarding Reports

Edwards¹,

Rogers²,

Camacho-Collados³

et al. 2020

Preprint

View full text Add to dashboard Cite

The task of text and sentence classification is associated with the need for large amounts of labelled training data. The acquisition of high volumes of labelled datasets can be expensive or unfeasible, especially for highly-specialised domains for which documents are hard to obtain. Research on the application of supervised classification based on small amounts of training data is limited. In this paper, we address the combination of state-of-the-art deep learning and classification methods and provide an insight into what combination of methods fit the needs of small, domain-specific, and terminologically-rich corpora. We focus on a real-world scenario related to a collection of safeguarding reports comprising learning experiences and reflections on tackling serious incidents involving children and vulnerable adults. The relatively small volume of available reports and their use of highly domainspecific terminology makes the application of automated approaches difficult. We focus on the problem of automatically identifying the main themes in a safeguarding report using supervised classification approaches. Our results show the potential of deep learning models to simulate subject-expert behaviour even for complex tasks with limited labelled data.

show abstract

Text Classification Based on Fuzzy Radial Basis Function

Cited by 2 publications

References 5 publications

Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification

Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification

Predicting Themes within Complex Unstructured Texts: A Case Study on Safeguarding Reports

Contact Info

Product

Resources

About