Text Augmentation Using BERT for Image Captioning

Atliha, Viktar; Šešok, Dmitrij

doi:10.3390/app10175978

Cited by 24 publications

(15 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, paper [21] employed object spatial relationship modeling for image captioning, specifically within the transformer encoder-decoder architecture by incorporating the object relation module within the transformer encoder. Paper [22] proposed the use of augmentation of image captions in a dataset including augmentation using BERT to improve a solution to the image captioning problem. Furthermore, paper [23] utilized two streams of transformer-based architecture: one for the visual part and another for the textual part.…”

Section: Image Captioning Using Transformermentioning

confidence: 99%

Bornon: Bengali Image Captioning with Transformer-Based Deep Learning Approach

et al. 2021

View full text Add to dashboard Cite

Image captioning using encoder-decoder-based approach where CNN is used as the Encoder and sequence generator like RNN as Decoder has proven to be very effective. However, this method has a drawback, that is, sequence needs to be processed in order. To overcome this drawback, some researchers have utilized the transformer model to generate captions from images using English datasets. However, none of them generated captions in Bengali using the transformer model. As a result, we utilized three different Bengali datasets to generate Bengali captions from images using the transformer model. Additionally, we compared the performance of the transformer-based model with a visual attention-based encoder-decoder approach. Finally, we compared the result of the transformer-based model with other models that employed different Bengali image captioning datasets.

show abstract

Section: Image Captioning Using Transformermentioning

confidence: 99%

Bornon: Bengali Image Captioning with Transformer-Based Deep Learning Approach

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Studies showed that using word embedding models, such as word2vec [34], can be competitive for synonym replacement tasks by leveraging the previously mentioned linguistic resources [35]. On the other hand, next to synonym replacement and word embeddings, recent studies use context-based language models to perform textual data augmentation [32], [36], [37]. One example of such a model is BERT (Bidirectional Encoder Representations from Transformers) [38].…”

Section: Automated Detection Of Reminiscence From Everyday Conversationsmentioning

confidence: 99%

Coping With Imbalanced Data in the Automated Detection of Reminiscence From Everyday Life Conversations of Older Adults

et al. 2021

View full text Add to dashboard Cite

Reminiscence-the act of recalling or telling others about relevant personal past experiencesplays an important role in the well-being of older adults. Therefore, it is relevant to develop intelligent systems aiming at improving the well-being of the elderly by reliably detecting reminiscence in their everyday life conversations. Data imbalance is one of the main challenges in the automatic detection of reminiscence from everyday conversations, as reminiscing is a rare event. In this paper, we address the problem by proposing a methodology for coping with imbalanced data in the detection of reminiscence in conversations of older adults. The methodology combines data augmentation using BERT (Bidirectional Encoder Representations from Transformer) and feature extraction techniques leveraging natural language processing for the German language. We evaluate the proposed methodology on a dataset comprising transcripts of social conversations of older adults held in German. We compare our results with a previous work addressing the problem on the same dataset and we show that our approach strongly outperforms the baseline. The results in this study may support the development of intelligent systems for the real-time detection of reminiscence in everyday life of older adults and the design of digital health interventions to support their well-being.INDEX TERMS Natural language processing, data augmentation, BERT, machine learning, reminiscence, well-being, older adults.

show abstract

“…BERT makes full use of a large number of unsupervised texts for self-supervised learning and encodes linguistic knowledge. Experiments demonstrate its superior performance on various NLP tasks 1 . Word2vec is a technique used to calculate word vectors 2 .…”

Section: Introductionmentioning

confidence: 99%

Research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching

Tang

Mou

Liu

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Due to its potential impact on business efficiency, automated customer complaint labeling and classification are of great importance for management decision making and business applications. The majority of the current research on automated labeling uses large and well-balanced datasets. However, customer complaint labels are hierarchical in structure, with many labels at the lowest hierarchy level. Relying on lower-level labels leads to small and imbalanced samples, thus rendering the current automatic labeling practices inapplicable to customer complaints. This article proposes an automatic labeling model incorporating the BERT and word2vec methods. The model is validated on electric utility customer complaint data. Within the model, the BERT method serves to obtain shallow text tags. Furthermore, text enhancement is used to mitigate the problem of imbalanced samples that emerge when the number of labels is large. Finally, the word2vec model is utilized for deep text analysis. Experiments demonstrate the proposed model's efficiency in automating customer complaint labeling. Consequently, the proposed model supports enterprises in improving their service quality while simultaneously reducing labor costs.

show abstract

Text Augmentation Using BERT for Image Captioning

Cited by 24 publications

References 37 publications

Bornon: Bengali Image Captioning with Transformer-Based Deep Learning Approach

Bornon: Bengali Image Captioning with Transformer-Based Deep Learning Approach

Coping With Imbalanced Data in the Automated Detection of Reminiscence From Everyday Life Conversations of Older Adults

Research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching

Contact Info

Product

Resources

About