Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2407.04858 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915162160627712 |
|---|---|
| author | José, Marcos M. Cação, Flávio N. Ribeiro, Maria F. Cheang, Rafael M. Pirozelli, Paulo Cozman, Fabio G. |
| author_facet | José, Marcos M. Cação, Flávio N. Ribeiro, Maria F. Cheang, Rafael M. Pirozelli, Paulo Cozman, Fabio G. |
| contents | This paper proposes a novel architecture to generate multi-hop answers to open domain questions that require information from texts and tables, using the Open Table-and-Text Question Answering dataset for validation and training. One of the most common ways to generate answers in this setting is to retrieve information sequentially, where a selected piece of data helps searching for the next piece. As different models can have distinct behaviors when called in this sequential information search, a challenge is how to select models at each step. Our architecture employs reinforcement learning to choose between different state-of-the-art tools sequentially until, in the end, a desired answer is generated. This system achieved an F1-score of 19.03, comparable to iterative systems in the literature. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04858 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Question Answering with Texts and Tables through Deep Reinforcement Learning José, Marcos M. Cação, Flávio N. Ribeiro, Maria F. Cheang, Rafael M. Pirozelli, Paulo Cozman, Fabio G. Computation and Language This paper proposes a novel architecture to generate multi-hop answers to open domain questions that require information from texts and tables, using the Open Table-and-Text Question Answering dataset for validation and training. One of the most common ways to generate answers in this setting is to retrieve information sequentially, where a selected piece of data helps searching for the next piece. As different models can have distinct behaviors when called in this sequential information search, a challenge is how to select models at each step. Our architecture employs reinforcement learning to choose between different state-of-the-art tools sequentially until, in the end, a desired answer is generated. This system achieved an F1-score of 19.03, comparable to iterative systems in the literature. |
| title | Question Answering with Texts and Tables through Deep Reinforcement Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.04858 |