Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.16937 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912008524267520 |
|---|---|
| author | Shen, Chong Zhou, Chenyue |
| author_facet | Shen, Chong Zhou, Chenyue |
| contents | In this work, we investigate the effectiveness of injecting external knowledge to a large language model (LLM) to identify semantic plausibility of simple events. Specifically, we enhance the LLM with fine-grained entity types, event types and their definitions extracted from an external knowledge base. These knowledge are injected into our system via designed templates. We also augment the data to balance the label distribution and adapt the task setting to real world scenarios in which event mentions are expressed as natural language sentences. The experimental results show the effectiveness of the injected knowledge on modeling semantic plausibility of events. An error analysis further emphasizes the importance of identifying non-trivial entity and event types. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_16937 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Plausible-Parrots @ MSP2023: Enhancing Semantic Plausibility Modeling using Entity and Event Knowledge Shen, Chong Zhou, Chenyue Computation and Language In this work, we investigate the effectiveness of injecting external knowledge to a large language model (LLM) to identify semantic plausibility of simple events. Specifically, we enhance the LLM with fine-grained entity types, event types and their definitions extracted from an external knowledge base. These knowledge are injected into our system via designed templates. We also augment the data to balance the label distribution and adapt the task setting to real world scenarios in which event mentions are expressed as natural language sentences. The experimental results show the effectiveness of the injected knowledge on modeling semantic plausibility of events. An error analysis further emphasizes the importance of identifying non-trivial entity and event types. |
| title | Plausible-Parrots @ MSP2023: Enhancing Semantic Plausibility Modeling using Entity and Event Knowledge |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.16937 |