Automatic Extraction of Relationships among Motivations, Emotions and Actions from Natural Language Texts
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909277586718720 |
|---|---|
| author | Yang, Fei |
| author_facet | Yang, Fei |
| contents | We propose a new graph-based framework to reveal relationships among motivations, emotions and actions explicitly given natural language texts. A directed acyclic graph is designed to describe human's nature. Nurture beliefs are incorporated to connect outside events and the human's nature graph. No annotation resources are required due to the power of large language models. Amazon Fine Foods Reviews dataset is used as corpus and food-related motivations are focused. Totally 92,990 relationship graphs are generated, of which 63% make logical sense. We make further analysis to investigate error types for optimization direction in future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00966 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automatic Extraction of Relationships among Motivations, Emotions and Actions from Natural Language Texts Yang, Fei Computation and Language We propose a new graph-based framework to reveal relationships among motivations, emotions and actions explicitly given natural language texts. A directed acyclic graph is designed to describe human's nature. Nurture beliefs are incorporated to connect outside events and the human's nature graph. No annotation resources are required due to the power of large language models. Amazon Fine Foods Reviews dataset is used as corpus and food-related motivations are focused. Totally 92,990 relationship graphs are generated, of which 63% make logical sense. We make further analysis to investigate error types for optimization direction in future research. |
| title | Automatic Extraction of Relationships among Motivations, Emotions and Actions from Natural Language Texts |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.00966 |