TextConvoNet:A Convolutional Neural Network based Architecture for Text Classification

Soni, Sanskar; Chouhan, Satyendra Singh; Rathore, Santosh Singh

doi:10.48550/arxiv.2203.05173

Cited by 3 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 "Example: Text classification using CNN" [5] fig. 2 "Example: Text classification using CNN" [5] "As a brief conclusion CNN can be described as " a series of filters of different sizes and shapes which convolve (roll over) the original sentence matrix to reduce it into further low dimension matrices. In text classification ConvNets are being applied to distributed and discrete word embedding .…”

Section: Convolutional Neural Network Working Principles and Possibil...mentioning

confidence: 99%

Neural networks reliability for feedback processing.

Ermakova

2024

Preprint

View full text Add to dashboard Cite

Nowadays neural networks are a powerful instrument involved in industry, medicine, and science. AI takes part in graphics design, medicine, natural text processing, video recognition, speech generation, autonomous driving, and numerous other fields. Might AI completely replace a human workforce in specific areas? Or does it stay as a mighty instrument to facilitate task execution? Firstly, I have analyzed CNN and RNN neural network structure. Secondly, I have described an experiment to process feedback with AI to check its reliability

show abstract

Section: Convolutional Neural Network Working Principles and Possibil...mentioning

confidence: 99%

Neural networks reliability for feedback processing.

Ermakova

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…TextConvoNet was selected for this work because, according to the authors, it outperforms state-of-the-art machine learning and deep learning models for text classification purposes 40 .…”

Section: Textconvonetmentioning

confidence: 99%

Relevance classification on service desk texts using Natural Language Processing

Degasperi,

Cavalieri,

Castro

2023

Preprint

View full text Add to dashboard Cite

Service desk systems have a vast and rich base of information, consisting of the history of calls made, which can and should be used as a reference base for subsequent calls. Common search tools, such as keyword searches, prove to be unfeasible in large datasets, in addition to being able to bring results not necessarily related to the problem. “State-of-the-art” techniques exist, but they require high computational and operational costs for their training and use. In this sense, the purpose of this work is to investigate the sensitivity of machine learning algorithms in finding the characteristic defined here as “relevance”: the characteristic of texts with knowledge that can be reused. The motivation is that non-relevant texts can be removed in advance from the database, allowing complex algorithms to be employed in a more condensed database, reducing computational costs. Tests were performed with several combinations between the TF-IDF vectorizer and the word embedding Doc2Vec and the classic classifiers Naive-Bayes, Adaptive Boosting, Random Forest, Stochastic Gradient Descent, Logistic Regression, Support Vector Machine and Light Gradient Boosting Machine, and the classifier TextConvoNet, an architecture based on Convolutional Neural Networks. The TextConvoNet classifier presented the best results, with metrics close to 0.93, showing that the concept is detectable and that the technique is viable for removing non-relevant texts from a database.

show abstract

“…In addition, considering a solid relationship between adjacent elements for text, convolutional neural networks (CNNs) are widely used to extract local semantic features at different levels to fully consider the context information of the target position (Soni, Chouhan, and Rathore 2022;Johnson and Zhang 2017;Kim 2014). In the tasks of time series forecasting, Li et al (Li et al 2019) propose a ConvTrans algorithm that uses a causal convolutional to solve the problems of local context.…”

Section: Introductionmentioning

confidence: 99%

SeDepTTS: Enhancing the Naturalness via Semantic Dependency and Local Convolution for Text-to-Speech Synthesis

Jiang

Gao

et al. 2023

AAAI

View full text Add to dashboard Cite

Self-attention-based networks have obtained impressive performance in parallel training and global context modeling. However, it is weak in local dependency capturing, especially for data with strong local correlations such as utterances. Therefore, we will mine linguistic information of the original text based on a semantic dependency and the semantic relationship between nodes is regarded as prior knowledge to revise the distribution of self-attention. On the other hand, given the strong correlation between input characters, we introduce a one-dimensional (1-D) convolution neural network (CNN) producing query(Q) and value(V) in the self-attention mechanism for a better fusion of local contextual information. Then, we migrate this variant of the self-attention networks to speech synthesis tasks and propose a non-autoregressive (NAR) neural Text-to-Speech (TTS): SeDepTTS. Experimental results show that our model yields good performance in speech synthesis. Specifically, the proposed method yields significant improvement for the processing of pause, stress, and intonation in speech.

show abstract

TextConvoNet:A Convolutional Neural Network based Architecture for Text Classification

Cited by 3 publications

References 37 publications

Neural networks reliability for feedback processing.

Neural networks reliability for feedback processing.

Relevance classification on service desk texts using Natural Language Processing

SeDepTTS: Enhancing the Naturalness via Semantic Dependency and Local Convolution for Text-to-Speech Synthesis

Contact Info

Product

Resources

About