The Devil in the Details: How defining an NLP task can undermine or catalyze its successful implementation

Abstract: 

"In the fast-evolving field of NLP system development the careful definition of the task an NLP system needs to solve plays a critical role in determining the system’s success or failure. Ambiguous, vague, or incomplete task definitions can lead to misaligned objectives, biased behaviour, and suboptimal model performance. Precise and well-thought tasks, on the other hand, can align system goals with practical needs, enable better data collection, and allow a more accurate prediction of the system’s performance in the real-world.

In this talk, we will delve into the intricate relationship between NLP task definition and the outcomes of NLP system development, exploring how the precise formulation of tasks can either propel or hinder progress. Through case studies and examples, attendees will understand how ambiguous or biased task definitions can lead to misguided model objectives, high data acquisition costs and misleading system evaluations, and learn how to strike the right balance between specificity and adaptability in NLP task design.

Session Outline:

Attendees will understand how ambiguous or biased task definitions can lead to misguided model objectives, high data acquisition costs and misleading system evaluations, and learn how to strike the right balance between specificity and adaptability in NLP task design

Bio: 

Panos Alexopoulos has been working since 2006 at the intersection of data, semantics, and software, building intelligent systems that deliver value to business and society. Born and raised in Athens, Greece, he currently works as Head of Ontology at Textkernel, in Amsterdam, Netherlands, where he leads a team of Data Professionals in developing and delivering a large cross-lingual Knowledge Graph in the HR and Recruitment domain. Panos holds a PhD in Knowledge Engineering and Management from National Technical University of Athens, and has published more than 60 papers at international conferences, journals and books. He is the author of the book “Semantic Modeling for Data – Avoiding Pitfalls and Breaking Dilemmas” (O’Reilly, 2020), and a regular speaker and trainer in both academic and industry venues.

Open Data Science

 

 

 

Open Data Science
One Broadway
Cambridge, MA 02142
info@odsc.com

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Youtube
Consent to display content from Youtube
Vimeo
Consent to display content from Vimeo
Google Maps
Consent to display content from Google