AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912013425311744 |
|---|---|
| author | Shi, Yuchen Jiang, Guochao Qiu, Tian Yang, Deqing |
| author_facet | Shi, Yuchen Jiang, Guochao Qiu, Tian Yang, Deqing |
| contents | The relation extraction (RE) in complex scenarios faces challenges such as diverse relation types and ambiguous relations between entities within a single sentence, leading to the poor performance of pure "text-in, text-out" language models (LMs). To address these challenges, in this paper, we propose an agent-based RE framework, namely AgentRE, which fully leverages the potential of large language models (LLMs) including memory, retrieval and reflection, to achieve RE in complex scenarios. Specifically, three major modules are built in AgentRE serving as the tools to help the agent acquire and process various useful information, thereby obtaining improved RE performance. Our extensive experimental results upon two datasets in English and Chinese demonstrate our AgentRE's superior performance, especially in low-resource scenarios. Additionally, the trajectories generated by AgentRE can be refined to construct a high-quality training dataset incorporating different reasoning methods, which can be used to fine-tune smaller models. Code is available at https://github.com/Lightblues/AgentRE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_01854 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction Shi, Yuchen Jiang, Guochao Qiu, Tian Yang, Deqing Computation and Language The relation extraction (RE) in complex scenarios faces challenges such as diverse relation types and ambiguous relations between entities within a single sentence, leading to the poor performance of pure "text-in, text-out" language models (LMs). To address these challenges, in this paper, we propose an agent-based RE framework, namely AgentRE, which fully leverages the potential of large language models (LLMs) including memory, retrieval and reflection, to achieve RE in complex scenarios. Specifically, three major modules are built in AgentRE serving as the tools to help the agent acquire and process various useful information, thereby obtaining improved RE performance. Our extensive experimental results upon two datasets in English and Chinese demonstrate our AgentRE's superior performance, especially in low-resource scenarios. Additionally, the trajectories generated by AgentRE can be refined to construct a high-quality training dataset incorporating different reasoning methods, which can be used to fine-tune smaller models. Code is available at https://github.com/Lightblues/AgentRE. |
| title | AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.01854 |