Semantic Compression With Large Language Models

no code implementations • 25 Apr 2023 • Henry Gilbert, Michael Sandborn, Douglas C. Schmidt, Jesse Spencer-Smith, Jules White

The rise of large language models (LLMs) is revolutionizing information retrieval, question answering, summarization, and code generation tasks.

Code Generation Information Retrieval +2

ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design

no code implementations • 11 Mar 2023 • Jules White, Sam Hays, Quchen Fu, Jesse Spencer-Smith, Douglas C. Schmidt

This paper presents prompt design techniques for software engineering, in the form of patterns, to solve common problems when using large language models (LLMs), such as ChatGPT to automate common software engineering activities, such as ensuring code is decoupled from third-party libraries and simulating a web application API before it is implemented.

A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT

no code implementations • 21 Feb 2023 • Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, Douglas C. Schmidt

This paper describes a catalog of prompt engineering techniques presented in pattern form that have been applied to solve common problems when conversing with LLMs.

Prompt Engineering Transfer Learning

NL2CMD: An Updated Workflow for Natural Language to Bash Commands Translation

2 code implementations • 15 Feb 2023 • Quchen Fu, Zhongwei Teng, Marco Georgaklis, Jules White, Douglas C. Schmidt

First, we describe a state-of-the-art translation model used to generate Bash Commands from the corresponding English text.

Code Translation Semantic Parsing +1

Deep Learning Models on CPUs: A Methodology for Efficient Training

no code implementations • 20 Jun 2022 • Quchen Fu, Ramesh Chukka, Keith Achorn, Thomas Atta-fosu, Deepak R. Canchi, Zhongwei Teng, Jules White, Douglas C. Schmidt

First, it presents a method for optimizing the training of deep learning models on Intel CPUs and a toolkit called ProfileDNN, which we developed to improve performance profiling.

A Transformer-based Approach for Translating Natural Language to Bash Commands

1 code implementation • 20th IEEE International Conference on Machine Learning and Applications - ICMLA 2021 • Quchen Fu, Zhongwei Teng, Jules White, Douglas C. Schmidt

This paper explores the translation of natural language into Bash Commands, which developers commonly use to accomplish command-line tasks in a terminal.

Code Translation Sentence +1

Complementing Handcrafted Features with Raw Waveform Using a Light-weight Auxiliary Model

1 code implementation • 6 Sep 2021 • Zhongwei Teng, Quchen Fu, Jules White, Maria Powell, Douglas C. Schmidt

Instead of evaluating handcrafted features and raw waveforms independently, this paper proposes an Auxiliary Rawnet model to complement handcrafted features with features learned from raw waveforms.

speech-recognition Speech Recognition +1

FastAudio: A Learnable Audio Front-End for Spoof Speech Detection

1 code implementation • 6 Sep 2021 • Quchen Fu, Zhongwei Teng, Jules White, Maria Powell, Douglas C. Schmidt

The FastAudio front-end achieves a relative improvement of 27% when compared with fixed front-ends, outperforming all other learnable front-ends on this task.

Speaker Identification Speaker Verification +1