Conceptual annotation of text patterns

Bashar, Abul; Li, Yuefeng; Shen, Yan; Gao, Yang; Huang, Wei

doi:10.1111/coin.12133

Cited by 4 publications

(2 citation statements)

References 53 publications

(131 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea of sequential pattern mining can be transposed to text analysis. In a text, the ordering of words or relevant elements in sentences is important (Bashar et al, 2017). Thus, sentences in a text are considered sequential data, with each one being a subsequence of words (Fournier-Viger et al, 2017).…”

Section: Sequential Pattern Miningmentioning

confidence: 99%

“…The support (or absolute support) of a sequence s a in a document D is defined as the number of sequences that contain s a , and is denoted by sup(s a ). In other words, sup(s a ) = |{s|s ⊆ s a ∧ s ∈ D}| (Bashar et al, 2017). The M SC + patterns proposed in this work are more elaborate in two senses: (i) they take into account the order of occurrence of the words, not just their co-occurrence in the documents; and (ii) M SC + pattern instances are compared in more subtle and abstract ways than word matching.…”

Section: Sequential Pattern Miningmentioning

confidence: 99%

See 1 more Smart Citation

MSC+: Language pattern learning for word sense induction and disambiguation

Goularte

Sorato

Nassar

et al. 2020

Knowledge-Based Systems

View full text Add to dashboard Cite

Section: Sequential Pattern Miningmentioning

confidence: 99%

Section: Sequential Pattern Miningmentioning

confidence: 99%

MSC+: Language pattern learning for word sense induction and disambiguation

Goularte

Sorato

Nassar

et al. 2020

Knowledge-Based Systems

View full text Add to dashboard Cite

Active Learning for Effectively Fine-Tuning Transfer Learning to Downstream Task

Bashar

Nayak

2021

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

Language model (LM) has become a common method of transfer learning in Natural Language Processing (NLP) tasks when working with small labeled datasets. An LM is pretrained using an easily available large unlabelled text corpus and is fine-tuned with the labelled data to apply to the target (i.e., downstream) task. As an LM is designed to capture the linguistic aspects of semantics, it can be biased to linguistic features. We argue that exposing an LM model during fine-tuning to instances that capture diverse semantic aspects (e.g., topical, linguistic, semantic relations) present in the dataset will improve its performance on the underlying task. We propose a Mixed Aspect Sampling (MAS) framework to sample instances that capture different semantic aspects of the dataset and use the ensemble classifier to improve the classification performance. Experimental results show that MAS performs better than random sampling as well as the state-of-the-art active learning models to abuse detection tasks where it is hard to collect the labelled data for building an accurate classifier.

show abstract

ALGAN: Time Series Anomaly Detection with Adjusted-LSTM GAN

Bashar,

Nayak

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Anomaly detection in time series data, to identify points that deviate from normal behaviour, is a common problem in various domains such as manufacturing, medical imaging, and cybersecurity. Recently, Generative Adversarial Networks (GANs) are shown to be effective in detecting anomalies in time series data. The neural network architecture of GANs (i.e. Generator and Discriminator) can significantly improve anomaly detection accuracy. In this paper, we propose a new GAN model, named Adjusted-LSTM GAN (ALGAN), which adjusts the output of an LSTM network for improved anomaly detection in both univariate and multivariate time series data in an unsupervised setting. We evaluate the performance of ALGAN on 46 real-world univariate time series datasets and a large multivariate dataset that spans multiple domains. Our experiments demonstrate that ALGAN outperforms traditional, neural network-based, and other GAN-based methods for anomaly detection in time series data.

show abstract

Conceptual annotation of text patterns

Cited by 4 publications

References 53 publications

MSC+: Language pattern learning for word sense induction and disambiguation

MSC+: Language pattern learning for word sense induction and disambiguation

Active Learning for Effectively Fine-Tuning Transfer Learning to Downstream Task

ALGAN: Time Series Anomaly Detection with Adjusted-LSTM GAN

Contact Info

Product

Resources

About