PromptChart: prompting InstructGPT for zero & few-shot chart question answering and summarization
Charts are commonly used in data analysis to summarize key insights and answer complex queries. However, comprehending charts through tasks such as chart question answering (CQA) and chart summarization (CS) can be cognitively intensive. Existing state-of-the-art models rely on fine-tuning strategie...
Saved in:
Main Author: | Do, Xuan Long |
---|---|
Other Authors: | Joty Shafiq Rayhan |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/166497 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Declaration-based prompt tuning for visual question answering
by: LIU, Yuhang, et al.
Published: (2022) -
Prompt to be consistent is better than self-consistent? Few-shot and zero-shot fact verification with pre-trained language models
by: ZENG, Fengzhu, et al.
Published: (2023) -
HGPrompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning
by: YU, Xingtong, et al.
Published: (2024) -
Virtual prompt pre-training for prototype-based few-shot relation extraction
by: He, Kai, et al.
Published: (2023) -
AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection
by: ZHOU, Qihang, et al.
Published: (2024)