Publications

Two-Step Classification using Recasted Data for Low Resource Settings

Published in 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, 2022

An NLP model’s ability to reason should be independent of language. Previous works utilize Natural Language Inference (NLI) to understand the reasoning ability of models, mostly focusing on high resource languages like English. To address scarcity of data in low-resource languages such as Hindi, we use data recasting to create NLI datasets for four existing text classification datasets. Through experiments, we show that our recasted dataset is devoid of statistical irregularities and spurious patterns. We further study the consistency in predictions of the textual entailment models and propose a consistency regulariser to remove pairwise-inconsistencies in predictions. We propose a novel two-step classification method which uses textual-entailment predictions for classification task. We further improve the performance by using a joint-objective for classification and textual entailment. We therefore highlight the benefits of data recasting and improvements on classification performance using our approach with supporting experimental results.

Recommended citation: Shagun Uppal , Vivek Gupta ,Avinash Swaminathan, Haimin Zhang, Debanjan Mahata, Rakesh Gosangi, Rajiv Ratn Shah, and Amanda Stent.Two-step classification using recasted data for low resource settings. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing , pages 706–719, Suzhou, China, December 2020. Association for Computational Linguistics. https://www.aclweb.org/anthology/2020.aacl-main.71.pdf

A Preliminary Exploration of GANs for Keyphrase Generation

Published in 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022

We introduce a new keyphrase generation approach using Generative Adversarial Networks (GANs). For a given document, the generator produces a sequence of keyphrases, and the discriminator distinguishes between human-curated and machinegenerated keyphrases. We evaluated this approach on standard benchmark datasets. We observed that our model achieves state-of-theart performance in the generation of abstractive keyphrases and is comparable to the best performing extractive techniques. Although we achieve promising results using GANs, they are not significantly better than the stateof-the-art generative models. To our knowledge, this is one of the first works that use GANs for keyphrase generation. We present a detailed analysis of our observations and expect that these findings would help other researchers to further study the use of GANs for the task of keyphrase generation.

Recommended citation: Avinash Swaminathan, Haimin Zhang, Debanjan Mahata, Rakesh Gosangi, Rajiv Ratn Shah, and Amanda Stent.A preliminary exploration of GANs for keyphrase generation. In Proceedings of the 2020 Conference onEmpirical Methods in Natural Language Processing (EMNLP), pages 8021–8030, Online, November 2020. Associationfor Computational Linguistics. https://www.aclweb.org/anthology/2020.emnlp-main.645.pdf

Keyphrase generation for scientific articles using gans (student abstract)

Published in AAAI Conference on Artificial Intelligence 2020, 2022

In this paper, we present a keyphrase generation approach using conditional Generative Adversarial Networks (GAN). In our GAN model, the generator outputs a sequence of keyphrases based on the title and abstract of a scientific article. The discriminator learns to distinguish between machine-generated and human-curated keyphrases. We evaluate this approach on standard benchmark datasets. Our model achieves state-of-the-art performance in generation of abstractive keyphrases and is also comparable to the best performing extractive techniques. We also demonstrate that our method generates more diverse keyphrases and make our implementation publicly available

Recommended citation: Swaminathan, A., Gupta, R. K., Zhang, H., Mahata, D., Gosangi, R., & Shah, R. R. (2020). Keyphrase Generation for Scientific Articles Using GANs (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence , 34(10), 13931-13932. https://doi.org/10.1609/aaai.v34i10.7238 https://ojs.aaai.org/index.php/AAAI/article/view/7238

Gender Classification using Facial Embeddings: A Novel Approach

Published in ELseveir Procedia Computer Science Journal, 2009

Image Processing for Human recognition involves using bio-metric traits such as Face, Iris, Voice and other physical traits to uniquely identify human faces. With the increase in Image Data on the Internet, there is a huge demand for Artificial Intelli-gence(AI) algorithms that can perform classification tasks like Race and Gender Classification. The advent of Deep Learning Techniques like Convolutional Networks has led to a rapid ascent in accuracy in various image classification tasks. Through this paper, a novel method to predict Gender of a person by applying various Machine Learning Classification Techniques on Facial Em-beddings has been proposed. The facial embeddings are found by passing through a Pretrained Inception Network. The maximum accuracy obtained by the proposed work to classify gender is 97%.

Recommended citation: Avinash Swaminathan , Mridul Chaba, Deepak Kumar Sharma,and Yogesh Chaba. Gender Classification using Facial Embeddings: A Novel Approach. Procedia Computer Science , 167:2634 – 2642, 2020. International Conference on Computational Intelligence and Data Science. https://www.sciencedirect.com/science/article/pii/S1877050920308085