About
I am passionate about building things, software and other, that improves human lives. I…
Services
Articles by Ankush
Activity
-
We’re pleased to announce Sunny R Gupta, 𝗦𝗲𝗻𝗶𝗼𝗿 𝗗𝗶𝗿𝗲𝗰𝘁𝗼𝗿 𝗼𝗳 𝗧𝗲𝗰𝗵𝗻𝗼𝗹𝗼𝗴𝘆 – 𝗖𝗿𝗶𝗰𝗶𝗻𝗳𝗼 & 𝗝𝗶𝗼𝗛𝗼𝘁𝘀𝘁𝗮𝗿 at…
We’re pleased to announce Sunny R Gupta, 𝗦𝗲𝗻𝗶𝗼𝗿 𝗗𝗶𝗿𝗲𝗰𝘁𝗼𝗿 𝗼𝗳 𝗧𝗲𝗰𝗵𝗻𝗼𝗹𝗼𝗴𝘆 – 𝗖𝗿𝗶𝗰𝗶𝗻𝗳𝗼 & 𝗝𝗶𝗼𝗛𝗼𝘁𝘀𝘁𝗮𝗿 at…
Liked by Ankush Dharkar
-
At ITM, we believe that the quality of an event is defined by the caliber of the minds that shape it. SummerHacks 2026, our flagship 24-hour…
At ITM, we believe that the quality of an event is defined by the caliber of the minds that shape it. SummerHacks 2026, our flagship 24-hour…
Liked by Ankush Dharkar
Experience
Education
Publications
-
Towards Efficient Named-Entity Rule Induction for Customizability
EMNLP 2012
Generic rule-based systems for Information Extraction (IE) have been shown to work reasonably well out-of-the-box, and achieve state-of-the-art accuracy with further domain customization. However, it is generally recognized that manually building and customizing rules is a complex and labor intensive process. In this paper, we discuss an approach that facilitates the process of building customizable rules for Named-Entity Recognition (NER) tasks via rule induction, in the Annotation Query…
Generic rule-based systems for Information Extraction (IE) have been shown to work reasonably well out-of-the-box, and achieve state-of-the-art accuracy with further domain customization. However, it is generally recognized that manually building and customizing rules is a complex and labor intensive process. In this paper, we discuss an approach that facilitates the process of building customizable rules for Named-Entity Recognition (NER) tasks via rule induction, in the Annotation Query Language (AQL). Given a set of basic features and an annotated document collection, our goal is to generate an initial set of rules with reasonable accuracy, that are interpretable and thus can be easily refined by a human developer. We present an efficient rule induction process, modeled on a fourstage manual rule development process and present initial promising results with our system. We also propose a simple notion of extractor complexity as a first step to quantify the interpretability of an extractor, and study the effect of induction bias and customization of basic features on the accuracy and complexity of induced rules. We demonstrate through experiments that the induced rules have good accuracy and low complexity according to our complexity measure.
Other authors -
Languages
-
English
Native or bilingual proficiency
Organizations
-
YUDEK
Yes
- Present
More activity by Ankush
-
Excited to be mentoring at OpenCode's first buildathon in India by GrowthX® this weekend. 100+ AI-first builders. 8 hours. $100K in cash & credits…
Excited to be mentoring at OpenCode's first buildathon in India by GrowthX® this weekend. 100+ AI-first builders. 8 hours. $100K in cash & credits…
Liked by Ankush Dharkar
-
Excited to mentor at the OpenCode X GrowthX® Buildathon this Sunday. 8 hours, builders leveraging AI to create something remarkable- looking…
Excited to mentor at the OpenCode X GrowthX® Buildathon this Sunday. 8 hours, builders leveraging AI to create something remarkable- looking…
Liked by Ankush Dharkar
-
Recently joined Team Shiksha, an open source community focused on building and learning together. I’ll be working with the team to manage projects…
Recently joined Team Shiksha, an open source community focused on building and learning together. I’ll be working with the team to manage projects…
Liked by Ankush Dharkar
-
The people who know you best have no way to prove it to the people who need to know. That's true in hiring, renting, dating, getting a loan.
The people who know you best have no way to prove it to the people who need to know. That's true in hiring, renting, dating, getting a loan.
Posted by Ankush Dharkar
-
The great thing about the internet is it's given access to everyone. The bad thing about the internet is it's given access to _everyone_.
The great thing about the internet is it's given access to everyone. The bad thing about the internet is it's given access to _everyone_.
Posted by Ankush Dharkar
-
Principle of mathematical induction If you've not read this in your school or forgotten it, this is a good topic to know about. This will simplify…
Principle of mathematical induction If you've not read this in your school or forgotten it, this is a good topic to know about. This will simplify…
Posted by Ankush Dharkar
Other similar profiles
Explore top content on LinkedIn
Find curated posts and insights for relevant topics all in one place.
View top content