Profile image of omerarshad
Flag of Pakistan Islamabad, Pakistan
Member since April 5, 2013
0 Recommendations


Online Offline
Experienced NLP/ML engineer with over 3 years of proven industry experience. I am expert at Text Classification, Semantic similarity, Sentiment Analysis , Summarization, Named Entity Recognition, Semantic Analysis/parsing. Information extraction from PDFs, Scanned documents. NLP tasks worked on : - Automated compliance verification - Semantic Textual Similarity - Semantic parsing/analysis of text - Resume parsing - Applying Named Entity Recognition (NER) to extract required information - Extracting structured text from PDF/Scan document - Text classification Projects worked on : - Automated Compliance verification - Insurance claims classification/ Extraction - Automated Resume shortlisting based on Description - Information extraction from payslips/bank statement
$40 USD/hr
2 reviews
  • 50%Jobs Completed
  • 100%On Budget
  • 100%On Time
  • 50%Repeat Hire Rate

Portfolio Items

Recent Reviews

  • image of Omer A. small script in python $7.00 USD

    “He really knows how to understand requirements and deliver on time. Hired him twice. Will hire him again. Great work!”

  • image of Omer A. Information extraction from PDF $30.00 USD

    “Experienced in Natural Language Processing tasks. On time in budget. Highly Recommended!”


ML/NLP engineer

Mar 2017

Development of an automated compliance checking system ([login to view URL]) using state of the art NLP and ML techniques. • Semantic parsing to extract structural information from text. • Representing text as knowledge graphs and building ontologies • Using transfer learning (fine-tuning pre-trained models) to improve generalization and performance. • Named tagging to extract useful information from free text.



2009 - 2013 (4 years)


2014 - 2016 (2 years)


Aiding Intra-Text Representations with Visual Context for Multimodal Named Entity Recognition

We propose an end to end model which learns a joint representation of a text and an image. Our model extends multi-dimensional self attention technique, where now image help to enhance relationship between words. Experiments show that our model is capable of capturing both textual and visual contexts with greater accuracy, achieving state-of-the-art results on Twitter multimodal Named Entity Recognition dataset


  • Facebook Connected
  • Preferred Freelancer
  • Payment Verified
  • Phone Verified
  • Identity Verified
  • Email Verified

My Top Skills

Browse Similar Freelancers