shubham-das Goto Github PK

background-generator

codeclash

emodetection

face-recognition-brain

Final project for Udemy course

face-recognition-brain-api

Final project for Udemy course

first-contributions

🚀✨ Help beginners contribute to open source projects

fooddemandclassifier

html-project

iim-capstone-project

learnhub

loan-classification

loanclassification

machine-learning-iim-i

shubham-das.github.io

stack-clone

start-here-guidelines

Guidelines on how this open source community works

text-audio-sentiment-analysis-using-cross-modal-bert

With the goal of enabling machines to perceive, understand, and express emotion, multimodal sentiment analysis is a young topic of study. We can learn more in-depth information about the speaker's emotional qualities through the cross-modal engagement. An effective pre-trained language representation model is called Bidirectional Encoder Representations from Transformers (BERT). On eleven natural language processing tasks, including question answering and natural language inference, fine-tuning has produced fresh, cutting-edge outcomes. Although the majority of earlier studies that improved BERT only used text data, it is still worthwhile to investigate how to learn a better representation by incorporating multimodal data. The Cross-Modal BERT (CM-BERT), which we suggest in this research, uses the interaction between text and audio modality to hone the pre-trained BERT model. Masked multimodal attention, the core aspect of CM-BERT, combines the information from text and audio modalities to dynamically modify the weight of words. On the open multimodal sentiment analysis datasets CMU-MOSI and CMU-MOSEI, we test our methodology. The findings of the experiment reveal that it has greatly outperformed prior baselines and text-only finetuning of BERT in terms of performance on all criteria. In addition, by using audio modality information, we demonstrate the masked multimodal attention and demonstrate that it can appropriately modify the weight of words.

travel-guide

"A travel guide to suggest activities you can do once you arrive to a certain destination. Or you can just browse destinations and check out the different available activities."