Avatar

Syeda Nahida Akter

Student at Masters of Language Technologies

Carnegie Mellon University

My research vision is to incorporate commonsense knowledge and social intelligence into an embodied agent by integrating information from multiple modalities. The questsions that I am broadly investigating during my research are:

  • How to refine visual grounding that - (a) understands the visual information in terms of relations, attributes and their correlations, (b) ensures proper semantic vision interpretation and alignment, and (c) is capable of grounding information locally and executing complex reasoning to summarize the global context?

  • How to establish an efficient, interpretable and compositional connection among language, vision, and social cognition so that - (a) interactions between natural language and vision ensure query understanding and answer formulation and (b) connections between vision and social cognition help to interpret intents and interactions?

I am currently a second year masters student (MLT) and an incoming Ph.D. student at Language Technologies Institute, Carnegie Mellon University. I am working on multimodal commonsense reasoning and social intelligence modeling under the supervision of Professor Eric Nyberg.

Apart from exploring plethora of exciting research problems, I love reading books, sketching, playing with charcoals, writing poems and reciting them. Robert Frost is my inspiration for writing. "And miles to go before I sleep, And miles to go before I sleep"...

Interests

  • Multimodal Commonsense Reasoning
  • Social Intelligence Modeling
  • Embodied AI

Education

  • Masters of Language Technologies (2021 - Present)

    Carnegie Mellon University

  • Undergrad Student in Computer Science (2016 - 2021)

    Bangaldesh University of Engineering and Technology

Recent News





Publications

(August 23-27, 2020). WeightGrad: Geo-Distributed Data Analysis Using Quantization for Faster Convergence and Better Accuracy. Proceedings of the 2020 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM SIGKDD 2020), San Diego, CA, USA..

PDF DOI

KnowUREnvironment: An Automated Knowledge Graph for Climate Change and Environmental Issues. The Role of AI in Responding to Climate Change, AAAI Fall Symposium Series, November 2022..

PDF





Research

WeightGrad: Geo-Distributed Data Analysis Using Quantization for Faster Convergence and Better Accuracy

High network communication cost for synchronizing weights and gradients in geo-distributed data analysis using DNN models consumes the benefits of advancement in computation and optimization techniques. Quantization methods for weight, gradient or both have been proved to be infeasible in terms of distributed training across multiple data centers all over the world. Here, we introduce WeightGrad which acknowledges the limitations of quantization and provides loss-aware weight-quantized networks with quantized gradients for local convergence and for global convergence it dynamically eliminates insignificant communication between data centers while still guaranteeing the correctness of DNN models. Our experiments on our developed prototypes of WeightGrad running across 3 Amazon EC2 regions shows that WeightGrad provides 1.06% gain in top-1 accuracy, 5.36× speedup over baseline and 1.4×-2.26× over the four state-of-the-art distributed ML systems.

BERT for Multilingual Commonsense and Contextual Q&A

Using multilingual pre-trained model XML-Roberta we develop a model for contextual commonsense based Question Answering(QA). We propose a new embedding layer with a topic modeling structure prior to that to increase accuracy for context-based question answering system for low resource languages. We address multiple persons/organizations/events in the context (create ambiguity while generating answer) issue by applying an attention layer followed by an entity extraction layer to ensure query-based tagging which will narrow down the search space and eliminate ambiguity. We are emphasizing on cost-effective well-structured fine-tuning steps rather than modifying the pretrained model to address challenges of incorporating commonsense into the language models.

Responding to the Stigma, Fear, Discrimination, and Misinformation Related to the COVID-19 Disease Outbreak

In this work, we use Natural Language Processing (NLP) and Social Network Analysis (SNA) to study collected anonymized Twitter data. The NLP performs the following procedures to analyze social media posts: keyword gathering, frequency analysis, information extraction, automatic categorization and clustering, automatic summarization, and finding associations within the data. The objective of these procedures would be to find how stigma manifests itself on social media. The SNA studies de-identified data to analyze and visualize existing network structures, along with mapping misinformation spread. The objective of these procedures is to understand how misinformation and stigmatization spread and change in social media channels. I am working on the NLP part of this project which includes experimenting different topic modeling architectures (LDA, GSDMM, BTM, lda2vec, BERT) for short texts like tweets, modeling advanced classifier as well as DNN architectures and showing comparison.

Phylogenetic Tree Estimation Using Deep Neural Network

Phylogenetic trees depict the evolution of a set of taxa from their most recent common ancestor. A species tree is a phylogenetic tree that models the evolutionary history of a set of species. A gene tree is a phylogenetic tree that models a genealogy of a gene. In this work, we intend to predict species tree from a set of gene trees. A wide array of algorithms and computer programs are available for inferring phylogenetic trees from various types of data. Though those algorithms work well with a fixed and small number of taxa, they perform poorly when the number of taxa increases. To acknowledge this problem of existing state-of-the-art algorithms, we use embedding based DNN models to predict a species tree from a set of gene trees for a wide range of taxa.

Malnutrition and Dehydration Detection From Body and Skin Images and Videos

The goal of this project is to build a mobile-Based application for detecting a clinical sign of malnutrition and dehydration and learn a new malnutrition and dehydration level detection scale based on the achieved accuracy of different clinical sign detection techniques. It captures image and video of specific body regions (face, lip, tongue, eye, fontanelle, urine and the video of skin turgor test) to detect a clinical sign of malnutrition and dehydration. We develop CNN model to extract features (e.g., body part detection, segmentation, color, border, shape and texture of skin) from images and videos and build a classifier (SVM) to predict malnutrition and dehydration level (mild, moderate, acute). This project is a collaboration with International Centre for Diarrhoeal Disease Research, Bangladesh [icddr,b].





Projects

 
 
 
 
 

Machine Learning Based Credit Risk Prediction System for Commercial Banks

Software Development Project (Collaboration with Bank Asia)

Feb 2019 – Dec 2020

A machine learning based banking software system (a collaboration with Bank Asia) which aims at predicting trustworthiness of a client who has applied for a loan by predicting credit risk. It also predicts the allowable loan amount that can be granted without causing any risk. I worked on the machine learning based backend system that included data cleaning, feature extraction, experimenting on different classifiers and regression models (random forest, decision tree, XGBoost). Our classifier gets 82% test accuracy (SOTA accuracy is 78% for the same dataset). [Repository]

 
 
 
 
 

ChatBot with Emotion

Hackathon Project

January 2019

A chatbot which processes texts using Natural Language API of Google and interacts accordingly, it takes picture of user and analyzes user's facial emotion using FACE API of Google and suggests user specific genre of songs or videos depending on the mood, it also takes voice command using Speech-to-Text and replies back to user using Text-to-Speech APIs of Google, it also stores the location of the user and suggests local songs, videos, sites etc. [Repository]

 
 
 
 
 

Tori: Mental Health Care App using Machine Learning

Hackathon Project

Jun 2018

Mental Health Care app using machine learning, it stores users activities on the mobile and interacts with users through a chatbot which collects textual responses from users and using NLP, tries to predict users' mood and conducts further interaction accordingly (e.g. sending songs, videos, sending suggestions to contact with close friends, informing users about time spent in mobiles each day etc.) [Repository]





Awards

  • KDD'20 Student Registration Award
  • University Merit Scholarship
  • Dean’s List Scholarship
  • Champion on CSE Fest Inter-University Hackathon, 2019
  • Champion on CSE Fest Inter-University Hackathon, 2018




Contact