activity
20162022
most citedEmotion-Aware Transformer Encoder for Empathetic Dialogue Generation

21 citations · 35 across the 3 of their papers we have counts for

collaborators

8 papers

cs.SD202221 cited

Emotion-Aware Transformer Encoder for Empathetic Dialogue Generation

Raman Goel, Seba Susan, Sachin Vashisht +1

Modern day conversational agents are trained to emulate the manner in which humans communicate. To emotionally bond with the user, these virtual agents need to be aware of the affe…

cs.CL20216 cited

Improving Word Recognition in Speech Transcriptions by Decision-level Fusion of Stemming and Two-way Phoneme Pruning

Sunakshi Mehra, Seba Susan

We introduce an unsupervised approach for correcting highly imperfect speech transcriptions based on a decision-level fusion of stemming and two-way phoneme pruning. Transcripts ar…

cs.CV2021

A Hybrid Model for Combining Neural Image Caption and k-Nearest Neighbor Approach for Image Captioning

Kartik Arora, Ajul Raj, Arun Goel +1

A hybrid model is proposed that integrates two popular image captioning methods to generate a text-based summary describing the contents of the image. The two image captioning mode…

cs.LG2021

Evaluating Deep Neural Network Ensembles by Majority Voting cum Meta-Learning scheme

Anmol Jain, Aishwary Kumar, Seba Susan

Deep Neural Networks (DNNs) are prone to overfitting and hence have high variance. Overfitted networks do not perform well for a new data instance. So instead of using a single DNN…

cs.LG20218 cited

A Novel Framework for Neural Architecture Search in the Hill Climbing Domain

Mudit Verma, Pradyumna Sinha, Karan Goyal +2

Neural networks have now long been used for solving complex problems of image domain, yet designing the same needs manual expertise. Furthermore, techniques for automatically gener…

cs.CL2021

Context- and Sequence-Aware Convolutional Recurrent Encoder for Neural Machine Translation

Ritam Mallick, Seba Susan, Vaibhaw Agrawal +2

Neural Machine Translation model is a sequence-to-sequence converter based on neural networks. Existing models use recurrent neural networks to construct both the encoder and decod…