Providing interpretability of document classification by deep neural network with self-attention
A Tamekuri, K Nakamura, Y Takahashi… - Journal of Information …, 2022 - jstage.jst.go.jp
Deep learning has been widely used in natural language processing (NLP) such as
document classification. For example, self-attention has achieved significant improvement in …
document classification. For example, self-attention has achieved significant improvement in …
A robust hybrid approach for textual document classification
Text document classification is an important task for diverse natural language processing
based applications. Traditional machine learning approaches mainly focused on reducing …
based applications. Traditional machine learning approaches mainly focused on reducing …
Text classification with improved word embedding and adaptive segmentation
Text classification first needs to convert the text into embedding vectors. Considering that
static word embedding models such as Word2vec do not consider the position information of …
static word embedding models such as Word2vec do not consider the position information of …
A survey on text document categorization using enhanced sentence vector space model and bi-gram text representation model based on novel fusion techniques
AD Amensisa, S Patil, P Agrawal - 2018 2nd International …, 2018 - ieeexplore.ieee.org
In this today's technology, many of digital documents are being generated and available
each day. However, it would cost a vast amount of time and human efforts to classify them in …
each day. However, it would cost a vast amount of time and human efforts to classify them in …
A comparative study on word embeddings in deep learning for text classification
Word embeddings act as an important component of deep models for providing input
features in downstream language tasks, such as sequence labelling and text classification …
features in downstream language tasks, such as sequence labelling and text classification …
DocNet: a document embedding approach based on neural networks
Z Mo, J Ma - 2018 24th International Conference on Automation …, 2018 - ieeexplore.ieee.org
Embedding texts into vector spaces is a common and fundamental preprocessing. Despite
there are several approaches to put documents into vectors, reducing the dimension and …
there are several approaches to put documents into vectors, reducing the dimension and …
[PDF][PDF] Doc2Sent2Vec: A Novel Two-Phase Approach for Learning Document Representation.
ABSTRACT Doc2Sent2Vec is an unsupervised approach to learn lowdimensional feature
vector (or embedding) for a document. This embedding captures the semantics of the …
vector (or embedding) for a document. This embedding captures the semantics of the …
Ukrainian news corpus as text classification benchmark
One of the crucial problems of natural language processing for languages such as Ukrainian
is lack of datasets both unlabeled (for pretraining of word embeddings or large deep …
is lack of datasets both unlabeled (for pretraining of word embeddings or large deep …
[HTML][HTML] CVs Classification Using Neural Network Approaches Combined with BERT and Gensim: CVs of Moroccan Engineering Students
Deep learning (DL)-oriented document processing is widely used in different fields for
extraction, recognition, and classification processes from raw corpus of data. The article …
extraction, recognition, and classification processes from raw corpus of data. The article …
A text representation model based on convolutional neural network and variational auto encoder
In the era of big data, the internet produces vast amounts of data every day, among which
text data occupies the main position. It is difficult for manual processing to deal with the …
text data occupies the main position. It is difficult for manual processing to deal with the …