Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916133496422400 |
|---|---|
| author | Li, Guozheng Ke, Wenjun Wang, Peng Xu, Zijie Ji, Ke Liu, Jiajun Shang, Ziyu Luo, Qiqing |
| author_facet | Li, Guozheng Ke, Wenjun Wang, Peng Xu, Zijie Ji, Ke Liu, Jiajun Shang, Ziyu Luo, Qiqing |
| contents | The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (\textsc{TableIE}) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I$^2$CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13741 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction Li, Guozheng Ke, Wenjun Wang, Peng Xu, Zijie Ji, Ke Liu, Jiajun Shang, Ziyu Luo, Qiqing Computation and Language Artificial Intelligence The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (\textsc{TableIE}) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I$^2$CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples. |
| title | Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2402.13741 |