Erweiterte Suche | Seiten im Überblick

NLP in Industry: challenges and best practices

Module Description

Lecturer	Daniel Dahlmeier
Module Type	Proseminar / Hauptseminar
Language	English
First Session	13.11.2020
Time and Place	Friday, 11:15-12:45, online auf heiCONF
Commitment Period	tbd.

Prerequisite for Participation

Mathematical Foundations of CL (or a comparable introductory class to linear algebra and theory of probability)

Programming I (Python)

Statistical Methods for CL (or a comparable introductory class to machine learning)

Assessment

Content

This seminar focuses on common challenges and best practices for natural language processing (NLP) in industry. NLP in industry comes with its own challenges, like data sparsity, data privacy regulations, and cost-benefit trade-offs. In this seminar, we discuss these challenges and technical approaches to overcome them. The seminar includes a practical project where participants propose a project, implement experiments and present the results to the class.

Module Overview

Agenda

Date	Session	Materials
13.11.2020 11:15–12:45	In this session, we will discuss general differences between academic research and industry, the current state of AI and NLP, and introduce the course project. Seminar logistics AI hype Research and innovation NLP in Industry Course Project	Lecture slides will be made available on heiBOX before the seminar.
20.11.2020 11:15–12:45	In this session, we will discuss the role of data and data protection regulation and examples of industry use cases. Data Industry Use Cases	Lecture slides will be made available on heiBOX before the seminar.
27.11.2020 11:15–12:45	In this session, we will talk in more detail about text classification and entity recognition and about advanced NLP topics for common requirements in industry applications. Text classification Entity Recognition Advanced NLP Topics	Lecture slides will be made available on heiBOX before the seminar.
04.12.2020 11:15–12:45	In this session, we will talk about the business value of NLP, common non-functional requirements, and give an overview about software engineering methodologies. The business case for NLP Non-functional requirements SCRUM, DevOps and all that	Lecture slides will be made available on heiBOX before the seminar.
22-26.02.2021 9:00-16:00	Block seminar for project presentations. Final schedule to be decided

Literature

• Daniel Jurafsky, James H. Martin. 2008. Speech and Language Processing (2nd Edition)
• Alfred Spector, Peter Norvig, and Slav Petrov. 2012.Google's hybrid approach to research. Communications of the ACM 55(7).
• Daniel Dahlmeier. 2017. On the Challenges of Translating NLP Research into Commercial Products. In Proceedings of ACL
• D. Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, and Michael Young. 2014. Machine learning: The high interest credit card of technical debt. In Proceedings of SE4ML: Software Engineering for Machine Learning (NIPS 2014 Workshop)

» More Materials