Aiding Intra-Text Representations with Visual Context for Multimodal Named Entity Recognition

Arshad, Omer; Gallo, Ignazio; Nawaz, Shah; Calefati, Alessandro

doi:10.48550/arxiv.1904.01356

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In multimodal interactivity, it calculates the matching between two features with a single attention, resulting in incorrect or incomplete attention. [31] Image captioning is a technique for creating a word from a visual area that is most closely related to the most recently generated term. With the purpose of obtaining richer semantic connections across multiple modalities, the proposed study employs an attention implementation similar to those employed in VQA.…”

Section: Introductionmentioning

confidence: 99%

Named Entity Recognition in Social Media Data

Sharma¹,

Shreya²,

Terni³

2022

IJRASET

View full text Add to dashboard Cite

In recent years, a lot of research is being carried out in the field of Named Entity Recognition of Social Media data. It is now easier for anyone to convey their opinions and information without any kind of authentication, rumours have multiplied as social media is now one of the commonly used media in the entire world. The fields in which Named Entity Recognition is used for analysis of data provided from various social media sites, include rumour detection, controversy detection, sentiment analysis, medical field (such as visualisation of the spread of COVID-19 or for various kinds of dietary concerns), topic detection and event detection. The purpose here is to present a summary of the present state of social media research and the impact created by information extracted from it. Through this paper, different methods proposed for the purpose of social media data extraction using Named Entity Recognition, have been studied in detail and a comparison has been provided for the same. Most of these papers use the most common metrics for evaluation of their performance, which includes precision, recall and accuracy. The proposed models have been tested on certain datasets extracted from social media networking sites such as twitter, facebook, etc. and their evaluated performance has been compared to the models proposed by several other similar approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Named Entity Recognition in Social Media Data

Sharma¹,

Shreya²,

Terni³

2022

IJRASET

View full text Add to dashboard Cite

show abstract

“…Typically, users combine text, image, audio or video to sell a product over an e-commence platform or express views on social media. The combination of these media types has been extensively studied to solve various tasks including classification [1], [2], [3], cross-modal retrieval [4] semantic relatedness [5], [6], image captioning [7], [8], multimodal named entity recognition [9], [10] and Visual Question Answering [11], [12]. In addition, multimodal data fueled an increased interest in generating images conditioned on natural language [13], [14].…”

Section: Introductionmentioning

confidence: 99%

Picture What You Read

Gallo

Nawaz

Calefati

et al. 2019

2019 Digital Image Computing: Techniques and Applications (DICTA)

Self Cite

View full text Add to dashboard Cite

Visualization refers to our ability to create an image in our head based on the text we read or the words we hear. It is one of the many skills that makes reading comprehension possible. Convolutional Neural Networks (CNN) are an excellent tool for recognizing and classifying text documents. In addition, it can generate images conditioned on natural language. In this work, we utilize CNNs capabilities to generate realistic images representative of the text illustrating the semantic concept. We conducted various experiments to highlight the capacity of the proposed model to generate representative images of the text descriptions used as input to the proposed model.

show abstract

Aiding Intra-Text Representations with Visual Context for Multimodal Named Entity Recognition

Cited by 2 publications

References 0 publications

Named Entity Recognition in Social Media Data

Named Entity Recognition in Social Media Data

Picture What You Read

Contact Info

Product

Resources

About