Ringki Das


2021

pdf bib
Image Caption Generation Framework for Assamese News using Attention Mechanism
Ringki Das | Thoudam Doren Singh
Proceedings of the 18th International Conference on Natural Language Processing (ICON)

Automatic caption generation is an artificial intelligence problem that falls at the intersection of computer vision and natural language processing. Although significant works have been reported in image captioning, the contribution is limited to English and few major languages with sufficient resources. But, no work on image captioning has been reported in a resource-constrained language like Assamese. With this inspiration, we propose an encoder-decoder based framework for image caption generation in the Assamese news domain. The VGG-16 pre-trained model at the encoder side and LSTM with an attention mechanism are employed at the decoder side to generate the Assamese caption. We train the proposed model on the dataset built in-house consisting of 10,000 images with a single caption for each image. We describe our experimental methodology, quantitative and qualitative results which validate the effectiveness of our model for caption generation. The proposed model shows a BLEU score of 12.1 outperforming the baseline model.

2020

pdf bib
NITS-Hinglish-SentiMix at SemEval-2020 Task 9: Sentiment Analysis for Code-Mixed Social Media Text Using an Ensemble Model
Subhra Jyoti Baroi | Nivedita Singh | Ringki Das | Thoudam Doren Singh
Proceedings of the Fourteenth Workshop on Semantic Evaluation

Sentiment Analysis refers to the process of interpreting what a sentence emotes and classifying them as positive, negative, or neutral. The widespread popularity of social media has led to the generation of a lot of text data and specifically, in the Indian social media scenario, the code-mixed Hinglish text i.e, the words of Hindi language, written in the Roman script along with other English words is a common sight. The ability to effectively understand the sentiments in these texts is much needed. This paper proposes a system titled NITS-Hinglish to effectively carry out the sentiment analysis of such code-mixed Hinglish text. The system has fared well with a final F-Score of 0.617 on the test data.