Zhengbao Jiang
Biographic Data
| ID | 10720432 |
|---|---|
| NAME | Zhengbao Jiang |
| GIVEN NAMES | Zhengbao |
| FAMILY NAME | Jiang |
| SIGNATURE | JIANG Z |
| AFFILIATIONS | Carnegie Mellon University, Pittsburgh, Pennsylvania, USA |
| ORCID | 0000-0002-0315-6727 |
| VERIFIED | No |
| TOTAL WORKS | 1 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 1 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2023 |
| LATEST PUBLICATION YEAR | 2023 |
| H-INDEX | 0 |
Pre-train, Prompt, and Predict
This article surveys and organizes research works in a new paradigm in natural language processing, which we dub “prompt-based learning.” Unlike traditional supervised learning, which trains a model to take in an input x and predict an output y as P ( y|x ), prompt-based learning is based on language models that model the probability of text directly. To use these models to perform prediction tasks, the original input x is modified using a templa…
No prominent works on this page.
Pre-train, Prompt, and Predict
This article surveys and organizes research works in a new paradigm in natural language processing, which we dub “prompt-based learning.” Unlike traditional supervised learning, which trains a model to take in an input x and predict an output y as P ( y|x ), prompt-based learning is based on language models that model the probability of text directly. To use these models to perform prediction tasks, the original input x is modified using a templa…
Artificial Intelligence (1 work) · Computer Science (1 work) · Cover (algebra) (1 work) · Field (mathematics) (1 work) · Function (biology) (1 work) · Language model (1 work) · Linguistics (1 work) · Natural language (1 work) · Natural language processing (1 work) · Natural Language Processing Techniques (1 work)