CodeKGC: Code Language Model for Generative Knowledge Graph Construction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914644477607936 |
|---|---|
| author | Bi, Zhen Chen, Jing Jiang, Yinuo Xiong, Feiyu Guo, Wei Chen, Huajun Zhang, Ningyu |
| author_facet | Bi, Zhen Chen, Jing Jiang, Yinuo Xiong, Feiyu Guo, Wei Chen, Huajun Zhang, Ningyu |
| contents | Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized texts or a specification language. However, large generative language model trained on structured data such as code has demonstrated impressive capability in understanding natural language for structural prediction and reasoning tasks. Intuitively, we address the task of generative knowledge graph construction with code language model: given a code-format natural language input, the target is to generate triples which can be represented as code completion tasks. Specifically, we develop schema-aware prompts that effectively utilize the semantic structure within the knowledge graph. As code inherently possesses structure, such as class and function definitions, it serves as a useful model for prior semantic structural knowledge. Furthermore, we employ a rationale-enhanced generation method to boost the performance. Rationales provide intermediate steps, thereby improving knowledge extraction abilities. Experimental results indicate that the proposed approach can obtain better performance on benchmark datasets compared with baselines. Code and datasets are available in https://github.com/zjunlp/DeepKE/tree/main/example/llm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_09048 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | CodeKGC: Code Language Model for Generative Knowledge Graph Construction Bi, Zhen Chen, Jing Jiang, Yinuo Xiong, Feiyu Guo, Wei Chen, Huajun Zhang, Ningyu Computation and Language Artificial Intelligence Information Retrieval Machine Learning Software Engineering Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized texts or a specification language. However, large generative language model trained on structured data such as code has demonstrated impressive capability in understanding natural language for structural prediction and reasoning tasks. Intuitively, we address the task of generative knowledge graph construction with code language model: given a code-format natural language input, the target is to generate triples which can be represented as code completion tasks. Specifically, we develop schema-aware prompts that effectively utilize the semantic structure within the knowledge graph. As code inherently possesses structure, such as class and function definitions, it serves as a useful model for prior semantic structural knowledge. Furthermore, we employ a rationale-enhanced generation method to boost the performance. Rationales provide intermediate steps, thereby improving knowledge extraction abilities. Experimental results indicate that the proposed approach can obtain better performance on benchmark datasets compared with baselines. Code and datasets are available in https://github.com/zjunlp/DeepKE/tree/main/example/llm. |
| title | CodeKGC: Code Language Model for Generative Knowledge Graph Construction |
| topic | Computation and Language Artificial Intelligence Information Retrieval Machine Learning Software Engineering |
| url | https://arxiv.org/abs/2304.09048 |