About Me

Dhruvesh Patel

Coming with an eclectic background involving robotics, software engineering, computer science, machine learning and natural language processing, currently, I am pursuing a master's degree in Computer Science at the University of Massachusetts Amherst focusing my coursework/projects on Machine Learning as applied to Natural Language Processing and Knowledge Graphs. My current research interests lie in the intersection of geometry, deep learning and NLP. I am broadly interested in:
1. Exploiting the geometry of non-euclidean spaces to provide better inductive bias to the representation models of natural language and Knowledge Graphs.
2. Evaluating and improving language understanding of deep learning models by providing the necessary inductive bias through architecture as well as data augmentation, mainly focusing on the task of Natural Language Inference, Reading Comprehension and Textual Summarization.
3. Integrating external knowledge sources like Knowledge Graphs, ontologies and hierarchies with deep learning models using end-to-end gradient based learning.

Currently, I am working as a NLP Research Intern at Abridge AI where I am responsible for designing models for Information Extraction and Summarization from healthcare conversations.

I was a summer research intern (2019) and continue to work as a Graduate Student Research Assistant at Information Extraction and Synthesis Lab (IESL) which is headed by Prof. Andrew McCallum.

Prior to starting my master's program, I worked in a small team at Kenome -- a nascent but extremely driven startup founded by Prof. Partha Talukdar -- solving challenging problems using Machine Learning and NLP. There I developed and deployed an RNN based time series prediction engine which utilizes structured time series data as well as unstructured textual data to make predictions about the time series.

I have also worked for ~2 years as a software engineer at MathWorks, focusing on developing Simulink and related products. This bolstered my knowledge of computer science and software development.

I started off my research career by working on computational aspects of robot kinematics and dynamics at the Robotics Lab., IIT Madras headed by Prof. Sandipan Bandyopadhyay.

Do click on the 'read more...' links and project icons below to know more about my work. To contact me use any of the social media links above.


  1. Representing Joint Hierarchies with Box Embeddings *Dhruvesh Patel , *Shib Sankar Dasgupta, Michael Boratko, Xiang Li, Luke Vilnis, and Andrew McCallum In Automated Knowledge Base Construction (AKBC) 2020 [Abstract] [URL] [Slides] [Video] [Code]

    Learning representations for hierarchical and multi-relational knowledge has emerged as an active area of research. Box Embeddings [Vilnis et al., 2018, Li et al., 2019] represent concepts with hyperrectangles in n-dimensional space and are shown to be capable of modeling tree-like structures efficiently by training on a large subset of the transitive closure of the WordNet hypernym graph. In this work, we evaluate the capability of box embeddings to learn the transitive closure of a tree-like hierarchical relation graph with far fewer edges from the transitive closure. Box embeddings are not restricted to tree-like structures, however, and we demonstrate this by modeling the WordNet meronym graph, where nodes may have multiple parents. We further propose a method for modeling multiple relations jointly in a single embedding space using box embeddings. In all cases, our proposed method outperforms or is at par with all other embedding methods.

  2. Computing the Safe Working Zone of a 3-RRS Parallel Manipulator Dhruvesh Patel , Rohit Kalla, Tetik Halil, Kiper Gökhan, and Sandipan Bandyopadhyay In New Trends in Mechanism and Machine Science 2017 [Abstract] [URL]

    Determination of the safe working zone (SWZ) of a parallel manipulator is a one-time computational task with several permanent benefits. As this subspace of the workspace of the manipulator is free of both the loss- and gain-type singularities, link interference, as well as physical joint limits, the manipulator can move freely in this space. Moreover, if the natural choice of a convex-shaped SWZ is adhered to, then point-to-point path planning inside the SWZ always has a trivial solution, namely, a segment joining the two points, which is guaranteed to be inside the workspace. In this paper, the SWZ of the 3-RRS existing in the İzmir Institute of Technology has been computed. Starting with the geometry of the manipulator, the loop-closure constraint equations have been derived. The singularity conditions are obtained based on the singularity of certain Jacobian matrices associated with the constraint functions. The interference between the links are detected by first encapsulating the links in rectangular parallelepipeds, which are then discretized into triangles, and subjected to collision tests between the relevant pairs of triangles. Using these theoretical developments, the SWZ is computed. The numerical results are depicted graphically.

Professional Journey

Information Extraction and Summarization for healthcare conversations.. read more May 2019 - Sep 2019
Natural Language Processing Research Intern

Working on learning and using representations of language data in non-euclidean spaces.. read more May 2019 - Sep 2019
Research Assistant

Working towards a master's degree in Computer Science with focus on ML and NLP.. read more Jan 2019 - present
Master of Science in Computer Science

Making sense of structured and unstructured data.. read more Mar 2018 - Jan 2019
Software Development Engineer, Machine Learning

Worked on development of Simulink and allied products. Mainly using C++... read more Jun 2016 - Jan 2018
Software Engineer

Analysis of Kinematics and Dynamics, Design, Interfacing and Control of a vehicle motion simulator based on a 3-DoF Parallel Manipulator... read more Dec 2014 - May 2015
Research and Design Engineer (Intern)

Trained for developing products, be it a software or a robot--taking it from need analysis to a final prototype and beyond. With a wide focus, learned basics of almost all the fields of engineering like computer science, electrical engineering and mechanical engineering. The interdisciplinary yet technical nature of the curriculum prepared me for diving deep into any field of engineering with focus on building products... read more Aug 2011 - Jul 2016
Dual Degree (Btech+Mtech) in Engineering Design with minor in Systems Engineering

My Projects

Weights and Biases with AllenNLP

Utilities and boilerplate code which allows using wandb to tune the hypereparameters for any AllenNLP model without a single line of extra code! read more...

...   ...

Natural Language Inference for Question Answering

Solving the task of Question Answering through the knowledge of inference
.

...   ...

Box Embedding for Knowledge Graph Completion

Improving KG representations using the inductive bias of Box Space, and analysing the issues with current datasets. read more...

...   ...

Using boxes for Natural Language Inference

Using Box representation for Natural Language Inference. This is an ongoing research project at IESL UMass with updates coming soon! read more...

...   ...

HyperA -- Attention in Hyperbolic Space

A pytorch implementation of Hyperbolic Neural Networks and attention mechanisms. Hyperbolic attention applied to the task of Natural Language Inference. read more...

...   ...


A c++ library for polynomial and matrix arithmetic, focused on applications in Robot Kinematics. read more...

...   ...


An intelligent debugger for C/C++ code on Linux

...   ...

Computing the safe working zone of parallel manipulators

Work in computational kinematics of parallel robot manipulators

...   ...

Experiments with TensorFlow

An aggregation of my experiments in Neural Networks and Deep Learning using TensorFlow read more...

...   ...

I-Glide, A Self-balancing Personal Transporter

Development of a product that addresses the short distance transportation (2-7 km) issues of people

...   ...

What am I reading?