Multi-Step Dialogue Workflow Action Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909104586358784 |
|---|---|
| author | Ramakrishnan, Ramya Elenberg, Ethan R. Narangodage, Hashan McDonald, Ryan |
| author_facet | Ramakrishnan, Ramya Elenberg, Ethan R. Narangodage, Hashan McDonald, Ryan |
| contents | In task-oriented dialogue, a system often needs to follow a sequence of actions, called a workflow, that complies with a set of guidelines in order to complete a task. In this paper, we propose the novel problem of multi-step workflow action prediction, in which the system predicts multiple future workflow actions. Accurate prediction of multiple steps allows for multi-turn automation, which can free up time to focus on more complex tasks. We propose three modeling approaches that are simple to implement yet lead to more action automation: 1) fine-tuning on a training dataset, 2) few-shot in-context learning leveraging retrieval and large language model prompting, and 3) zero-shot graph traversal, which aggregates historical action sequences into a graph for prediction. We show that multi-step action prediction produces features that improve accuracy on downstream dialogue tasks like predicting task success, and can increase automation of steps by 20% without requiring as much feedback from a human overseeing the system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_09593 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Multi-Step Dialogue Workflow Action Prediction Ramakrishnan, Ramya Elenberg, Ethan R. Narangodage, Hashan McDonald, Ryan Computation and Language Artificial Intelligence In task-oriented dialogue, a system often needs to follow a sequence of actions, called a workflow, that complies with a set of guidelines in order to complete a task. In this paper, we propose the novel problem of multi-step workflow action prediction, in which the system predicts multiple future workflow actions. Accurate prediction of multiple steps allows for multi-turn automation, which can free up time to focus on more complex tasks. We propose three modeling approaches that are simple to implement yet lead to more action automation: 1) fine-tuning on a training dataset, 2) few-shot in-context learning leveraging retrieval and large language model prompting, and 3) zero-shot graph traversal, which aggregates historical action sequences into a graph for prediction. We show that multi-step action prediction produces features that improve accuracy on downstream dialogue tasks like predicting task success, and can increase automation of steps by 20% without requiring as much feedback from a human overseeing the system. |
| title | Multi-Step Dialogue Workflow Action Prediction |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2311.09593 |