A Balanced and Broadly Targeted Computational Linguistics Curriculum
This paper describes the primarily-graduate computational linguistics and NLP curriculum at Georgetown University, a U.S. university that has seen significant growth in these areas in recent years. We reflect on the principles behind our curriculum choices, including recognizing the various academic backgrounds and goals of our students; teaching a variety of skills with an emphasis on working directly with data; encouraging collaboration and interdisciplinary work; and including languages beyond English. We reflect on challenges we have encountered, such as the difficulty of teaching programming skills alongside NLP fundamentals, and discuss areas for future growth.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SyntaxGym: An Online Platform for Targeted Evaluation of Language Models
Targeted syntactic evaluations have yielded insights into the generalizations learned by neural network language models. However, this line of research requires an uncommon confluence of skills: both the theoretical know…
Experimental DesignLanguage ModelingLanguage ModellingA Crash Course on Ethics for Natural Language Processing
It is generally agreed upon in the natural language processing (NLP) community that ethics should be integrated into any curriculum. Being aware of and understanding the relevant core concepts is a prerequisite for follo…
EthicsProgressive Growing of Patch Size: Curriculum Learning for Accelerated and Improved Medical Image Segmentation
In this work, we introduce Progressive Growing of Patch Size, an automatic curriculum learning approach for 3D medical image segmentation. Our approach progressively increases the patch size during model training, result…
Medical Image SegmentationLesion SegmentationAdvancing the Database of Cross-Linguistic Colexifications with New Workflows and Data
Lexical resources are crucial for cross-linguistic analysis and can provide new insights into computational models for natural language learning. Here, we present an advanced database for comparative studies of words wit…
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR
Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science. However, the training curriculum (how o…
Reinforcement Learning