ChartDialogs: Plotting from Natural Language Instructions
| Autor: | Yutong Shao, Ndapa Nakashole |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Carry (arithmetic) 020207 software engineering 02 engineering and technology computer.software_genre Plot (graphics) Task (project management) 020204 information systems 0202 electrical engineering electronic engineering information engineering Artificial intelligence Dialog box business computer Natural language processing Natural language |
| Zdroj: | ACL |
| DOI: | 10.18653/v1/2020.acl-main.328 |
| Popis: | This paper presents the problem of conversational plotting agents that carry out plotting actions from natural language instructions. To facilitate the development of such agents, we introduce ChartDialogs, a new multi-turn dialog dataset, covering a popular plotting library, matplotlib. The dataset contains over 15,000 dialog turns from 3,200 dialogs covering the majority of matplotlib plot types. Extensive experiments show the best-performing method achieving 61% plotting accuracy, demonstrating that the dataset presents a non-trivial challenge for future research on this task. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|