Avatar

Anmol Goel

Undergraduate Researcher

Precog, IIIT Delhi

About Me

I am a final year CS undergrad in New Delhi and a research intern at Precog Lab, IIIT Delhi under the supervision of Dr. Ponnurangam Kumaraguru. Previously, I worked with Dr. Saher Mehdi at WellOwise in IIIT Delhi at the intersection of NLP and healthcare. I am lucky to be advised by Dr. Chanchal Sharma at DRDO, India during my sophomore year.

Currently I am working on knowledge graphs and deep embedding kernels to model noisy user generated data.

hello world

Interests

  • Graph Neural Networks
  • Knowledge Graphs
  • NLP for Low Resource Languages
  • Theoretical Deep Learning

Education

  • Bachelor of Technology (CS), 2021

    GGSIPU, Delhi

Updates

  • Dec 2020 Presented a EMNLP’20 paper at our lab’s reading group. [Slides]
  • Nov 2020 One paper accepted at AAAI 2021 as student abstract.
  • Nov 2020 One paper accepted at NeurIPS 2020 DiffGeo4DL workshop
  • Oct 2020 One paper accepted at ACM CoDS-COMAD 2021 (YRS)
  • Oct 2020 Awarded travel grant to attend NeurIPS 2020 and ICML 2020.
  • Jul 2020: Volunteering at ACL 2020.
  • Jun 2020: Accepted into the RegML Summer School 2020

Recent Publications

Quickly discover relevant content by filtering publications.
Anmol Goel, Ponnurangam Kumaraguru (2021). Detecting Lexical Semantic Change across Corpora with Smooth Manifolds (Student Abstract). In 35th AAAI Conference on Artificial Intelligence, 2021.

Anmol Goel, Ponnurangam Kumaraguru (2021). A Geometric Measure of Polysemy in Hindi Language. In ACM IKDD CoDS-COMAD 2021 (YRS).

PDF Slides DOI

Anmol Goel, Ponnurangam Kumaraguru (2020). Leveraging Smooth Manifolds for Lexical Semantic Change Detection across Corpora. In NeurIPS 2020, DiffGeo4DL Workshop.

PDF Slides

Recent Posts

On the behaviour of high-dimensional normal distributions

Where in $\mathcal{R}^n$ is a high-dimensional random normal vector likely to be located?
Last updated on Jul 25, 2020 5 min read

Research

Knowledge Graphs

Improving knowledge graph methods

Low resource and Code-mixed NLP

Analysing language in low resource and code switched settings

Non-Euclidean Machine Learning

ML on graphs, ML on manifolds.