Masters in Computer Science, Focus on Natural Language Processing, Experience with Deep Learning Methods used for NLP.
Current Research Project: https://github.com/karishmamalkan/SDPNeuralTuringMachine
Wrote the baseline multi GPU sequence to sequence RNN architecture for Speech Recognition using MXNet for OpenSpeech
•
Improved existing monotonic attention in a way specifically useful for ASR which achieved a 3% relative word-error-rate improvement over initial implementation
•
Mentored intern project to improve performance of RNN-Transducer for Speech Recognition by modifying the loss to include sampled paths generated by the model during training
•
Experimenting with downsampling on encoder side using CNNs, minimum risk training and other enhancements to the baseline seq-to-seq architecture to improve WER scores
Technologies: MXNet – Deep Learning Framework, AWS
Neural Machine Translation
•
Improved MT models for Indonesian language from 18 BLEU -> 31 BLEU for AWS customer
•
BLEU score improvement gained by implementing the following techniques: Finetuning on domain specific data, using single language corpus in a parallel setting by backtranslation, ensembling.
