Chetanya Rastogi | Indian Institute Of Technology, Roorkee (original) (raw)

Uploads

Papers by Chetanya Rastogi

We present Chirpy Cardinal, an open-domain social chatbot. Aiming to be both informative and conv... more We present Chirpy Cardinal, an open-domain social chatbot. Aiming to be both informative and conversational, our bot chats with users in an authentic, emotionally intelligent way. By integrating controlled neural generation with scaffolded, handwritten dialogue, we let both the user and bot take turns driving the conversation, producing an engaging and socially fluent experience. Deployed in the fourth iteration of the Alexa Prize Socialbot Grand Challenge, Chirpy Cardinal handled thousands of conversations per day, placing second out of nine bots with an average user rating of 3.58/5.

ArXiv, 2020

This paper tackles one of the greatest limitations in Machine Learning: Data Scarcity. Specifical... more This paper tackles one of the greatest limitations in Machine Learning: Data Scarcity. Specifically, we explore whether high accuracy classifiers can be built from small datasets, utilizing a combination of data augmentation techniques and machine learning algorithms. In this paper, we experiment with Easy Data Augmentation (EDA) and Backtranslation, as well as with three popular learning algorithms, Logistic Regression, Support Vector Machine (SVM), and Bidirectional Long Short-Term Memory Network (Bi-LSTM). For our experimentation, we utilize the Wikipedia Toxic Comments dataset so that in the process of exploring the benefits of data augmentation, we can develop a model to detect and classify toxic speech in comments to help fight back against cyberbullying and online harassment. Ultimately, we found that data augmentation techniques can be used to significantly boost the performance of classifiers and are an excellent strategy to combat lack of data in NLP problems.

In many applications, such as scientific literature management, researcher search, social network... more In many applications, such as scientific literature management, researcher search, social network analysis and etc, Name Disambiguation (aiming at disambiguating WhoIsWho) has been a challenging problem. In addition, the growth of scientific literature makes the problem more difficult and urgent. Although name disambiguation has been extensively studied in academia and industry, the problem has not been solved well due to the clutter of data and the complexity of the same name scenario. In this work, we aim to explore models that can perform the task of name disambiguation using the network structure that is intrinsic to the problem and present an analysis of the models.

2018 International Joint Conference on Neural Networks (IJCNN), 2018

This paper presents a novel system for performing the task of image to image translation using Ge... more This paper presents a novel system for performing the task of image to image translation using Generative Adversarial Networks(GANs) while having very few training parameters and still maintaining acceptable results. The system learns the loss function by itself depending upon the translation task. Reduction in the number of parameters is achieved by modifying and using Fire modules like the ones used in the SqueezeNet architecture. This reduction results in a decrease in the training time of the model and also reducing its size, thus, making it feasible for deploying on hardware devices with limited memory. Results of a few datasets have been displayed and the model has also been evaluated for the task of automatic image colorization by means of a “colorization Turing test” where human participants were asked to rate the images(both generated and real) on the basis of its “realness”. A new method has been proposed for the quantitative evaluation of these results which, we believe, ...

Recent trends in NLP have shown remarkable success across diverse set of tasks by virtue of pre-t... more Recent trends in NLP have shown remarkable success across diverse set of tasks by virtue of pre-training transformer-based architectures [1] across a large corpora. One such architecture, multilingual-BERT (mBERT), has been shown to exhibit surprising cross-lingual abilities even in the absence of any cross-lingual training objective or aligned data. In this project, we work with a new cross-lingual QA dataset (TyDiQA-GoldP [2]) with an aim to investigate the cross-lingual transferability of mBERT by performing various experiments and ablation studies. Our experiments not only reveal excellent cross-lingual abilities of mBERT via zeroshot experiments but also discover that ensembling, gradient accumulation, and task specific knowledge transfer from a different cross-lingual dataset improves mBERT’s performance drastically and resulted in a 3.2 points of absolute improvement on F1 score over baseline. We realise that mBERT’s learning ability can be decoupled into task specific and la...

Scientific Reports, 2021

One of the lessons from the COVID-19 pandemic is the importance of social distancing, even in cha... more One of the lessons from the COVID-19 pandemic is the importance of social distancing, even in challenging circumstances such as pre-hurricane evacuation. To explore the implications of integrating social distancing with evacuation operations, we describe this evacuation process as a Capacitated Vehicle Routing Problem (CVRP) and solve it using a DNN (Deep Neural Network)-based solution (Deep Reinforcement Learning) and a non-DNN solution (Sweep Algorithm). A central question is whether Deep Reinforcement Learning provides sufficient extra routing efficiency to accommodate increased social distancing in a time-constrained evacuation operation. We found that, in comparison to the Sweep Algorithm, Deep Reinforcement Learning can provide decision-makers with more efficient routing. However, the evacuation time saved by Deep Reinforcement Learning does not come close to compensating for the extra time required for social distancing, and its advantage disappears as the emergency vehicle c...

2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE), 2016

The primary aim of the piece of work is to classify the extension and flexion positions of thumb,... more The primary aim of the piece of work is to classify the extension and flexion positions of thumb, index finger and middle finger by the use of EEG Signal. The EEG Signal of a human subject is recorded and used for offline training of a feedforward neural network which is used to learn the relation between EEG and finger motion. Six features have been extracted per sample of EEG signal over 10 channels, that is, signal from 10 different regions of the brain. Analysis of the data from these 10 channels revealed a certain few important channels which have been then selected for feature extraction and training of neural network. Observations show that flexion and extension positions of these three fingers are classified successfully. This idea can be developed further to combine these classified positions to perform tasks such as object translation and rotation using a finger exoskeleton.

In this paper, we present the second iteration of Chirpy Cardinal, an open-domain dialogue agent ... more In this paper, we present the second iteration of Chirpy Cardinal, an open-domain dialogue agent developed for the Alexa Prize SGC4 competition. Building on the success of the SGC3 Chirpy, we focus on improving conversational flexibility, initiative, and coherence. We introduce a variety of methods for controllable neural generation, ranging from prefix-based neural decoding over a symbolic scaffolding, to pure neural modules, to a novel hybrid infilling-based method that combines the best of both worlds. Additionally, we enhance previous news, music and movies modules with new APIs, as well as make major improvements in entity linking, topical transitions, and latency. Finally, we expand the variety of responses via new modules that focus on personal issues, sports, food, and even extraterrestrial life! These components come together to create a refreshed Chirpy Cardinal that is able to initiate conversations filled with interesting facts, engaging topics, and heartfelt responses.

We present Chirpy Cardinal, an open-domain social chatbot. Aiming to be both informative and conv... more We present Chirpy Cardinal, an open-domain social chatbot. Aiming to be both informative and conversational, our bot chats with users in an authentic, emotionally intelligent way. By integrating controlled neural generation with scaffolded, handwritten dialogue, we let both the user and bot take turns driving the conversation, producing an engaging and socially fluent experience. Deployed in the fourth iteration of the Alexa Prize Socialbot Grand Challenge, Chirpy Cardinal handled thousands of conversations per day, placing second out of nine bots with an average user rating of 3.58/5.

ArXiv, 2020

This paper tackles one of the greatest limitations in Machine Learning: Data Scarcity. Specifical... more This paper tackles one of the greatest limitations in Machine Learning: Data Scarcity. Specifically, we explore whether high accuracy classifiers can be built from small datasets, utilizing a combination of data augmentation techniques and machine learning algorithms. In this paper, we experiment with Easy Data Augmentation (EDA) and Backtranslation, as well as with three popular learning algorithms, Logistic Regression, Support Vector Machine (SVM), and Bidirectional Long Short-Term Memory Network (Bi-LSTM). For our experimentation, we utilize the Wikipedia Toxic Comments dataset so that in the process of exploring the benefits of data augmentation, we can develop a model to detect and classify toxic speech in comments to help fight back against cyberbullying and online harassment. Ultimately, we found that data augmentation techniques can be used to significantly boost the performance of classifiers and are an excellent strategy to combat lack of data in NLP problems.

In many applications, such as scientific literature management, researcher search, social network... more In many applications, such as scientific literature management, researcher search, social network analysis and etc, Name Disambiguation (aiming at disambiguating WhoIsWho) has been a challenging problem. In addition, the growth of scientific literature makes the problem more difficult and urgent. Although name disambiguation has been extensively studied in academia and industry, the problem has not been solved well due to the clutter of data and the complexity of the same name scenario. In this work, we aim to explore models that can perform the task of name disambiguation using the network structure that is intrinsic to the problem and present an analysis of the models.

2018 International Joint Conference on Neural Networks (IJCNN), 2018

This paper presents a novel system for performing the task of image to image translation using Ge... more This paper presents a novel system for performing the task of image to image translation using Generative Adversarial Networks(GANs) while having very few training parameters and still maintaining acceptable results. The system learns the loss function by itself depending upon the translation task. Reduction in the number of parameters is achieved by modifying and using Fire modules like the ones used in the SqueezeNet architecture. This reduction results in a decrease in the training time of the model and also reducing its size, thus, making it feasible for deploying on hardware devices with limited memory. Results of a few datasets have been displayed and the model has also been evaluated for the task of automatic image colorization by means of a “colorization Turing test” where human participants were asked to rate the images(both generated and real) on the basis of its “realness”. A new method has been proposed for the quantitative evaluation of these results which, we believe, ...

Recent trends in NLP have shown remarkable success across diverse set of tasks by virtue of pre-t... more Recent trends in NLP have shown remarkable success across diverse set of tasks by virtue of pre-training transformer-based architectures [1] across a large corpora. One such architecture, multilingual-BERT (mBERT), has been shown to exhibit surprising cross-lingual abilities even in the absence of any cross-lingual training objective or aligned data. In this project, we work with a new cross-lingual QA dataset (TyDiQA-GoldP [2]) with an aim to investigate the cross-lingual transferability of mBERT by performing various experiments and ablation studies. Our experiments not only reveal excellent cross-lingual abilities of mBERT via zeroshot experiments but also discover that ensembling, gradient accumulation, and task specific knowledge transfer from a different cross-lingual dataset improves mBERT’s performance drastically and resulted in a 3.2 points of absolute improvement on F1 score over baseline. We realise that mBERT’s learning ability can be decoupled into task specific and la...

Scientific Reports, 2021

One of the lessons from the COVID-19 pandemic is the importance of social distancing, even in cha... more One of the lessons from the COVID-19 pandemic is the importance of social distancing, even in challenging circumstances such as pre-hurricane evacuation. To explore the implications of integrating social distancing with evacuation operations, we describe this evacuation process as a Capacitated Vehicle Routing Problem (CVRP) and solve it using a DNN (Deep Neural Network)-based solution (Deep Reinforcement Learning) and a non-DNN solution (Sweep Algorithm). A central question is whether Deep Reinforcement Learning provides sufficient extra routing efficiency to accommodate increased social distancing in a time-constrained evacuation operation. We found that, in comparison to the Sweep Algorithm, Deep Reinforcement Learning can provide decision-makers with more efficient routing. However, the evacuation time saved by Deep Reinforcement Learning does not come close to compensating for the extra time required for social distancing, and its advantage disappears as the emergency vehicle c...

2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE), 2016

The primary aim of the piece of work is to classify the extension and flexion positions of thumb,... more The primary aim of the piece of work is to classify the extension and flexion positions of thumb, index finger and middle finger by the use of EEG Signal. The EEG Signal of a human subject is recorded and used for offline training of a feedforward neural network which is used to learn the relation between EEG and finger motion. Six features have been extracted per sample of EEG signal over 10 channels, that is, signal from 10 different regions of the brain. Analysis of the data from these 10 channels revealed a certain few important channels which have been then selected for feature extraction and training of neural network. Observations show that flexion and extension positions of these three fingers are classified successfully. This idea can be developed further to combine these classified positions to perform tasks such as object translation and rotation using a finger exoskeleton.

In this paper, we present the second iteration of Chirpy Cardinal, an open-domain dialogue agent ... more In this paper, we present the second iteration of Chirpy Cardinal, an open-domain dialogue agent developed for the Alexa Prize SGC4 competition. Building on the success of the SGC3 Chirpy, we focus on improving conversational flexibility, initiative, and coherence. We introduce a variety of methods for controllable neural generation, ranging from prefix-based neural decoding over a symbolic scaffolding, to pure neural modules, to a novel hybrid infilling-based method that combines the best of both worlds. Additionally, we enhance previous news, music and movies modules with new APIs, as well as make major improvements in entity linking, topical transitions, and latency. Finally, we expand the variety of responses via new modules that focus on personal issues, sports, food, and even extraterrestrial life! These components come together to create a refreshed Chirpy Cardinal that is able to initiate conversations filled with interesting facts, engaging topics, and heartfelt responses.