Kavita Ganeshan

LLM for Generative QA on Long Documents Recently I was working on a problem statement that needed to explore LLM for Question Answering context. The problem was to use opensource LLM model (not Open AI gpt) and host in a local system for QA on custom data. I found very...

I am so excited to share that I have been accepted to the LxMLS 2021 - Lisbon Machine learning School. I received their email today and have been in cloud 9 since. I have been following this summer school and few more since 5 years now. Finally I got an...

Summaries of literature survey on “Comparison of 2 Documents” Paper Title : Unstructured document compliance checking Entity: IBM China Publication: IJCAI 2020 Solution: It provides multi-level deep semantic comparison. 1. Sentence Level -> GNN based syntactic sentence encoder to capture semantic and syntactic clues of sentences. Dataset: Banking, open domain...

What I learnt when Remote engineer ran my NLP code and helped her troubleshoot. Background As part of my work, I was asked to deliver a Context based search on few contract documents. I developed an Elastic Search based solution. Nothing fancy. I coded the application in python, got the...

Interesting problems Semantic Search in Unstructured documents Important KEYWORD EXTRACTOR Extractor-Github-link Extractor-Github-link Unsupervised Approach for Automatic Keyword Extraction using Text Features. YAKE Abbreviations expansion Building dictionary / vocabulary single words 1. Using our custom built word2vec using GENSIM + Spacy 1. spacy vector similarity learn phrases 1. link-1 1. link-2...