Demonstrating Mutual Reinforcement Effect through Information Flow
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916275541770240 |
|---|---|
| author | Gan, Chengguang He, Xuzheng Zhang, Qinghao Mori, Tatsunori |
| author_facet | Gan, Chengguang He, Xuzheng Zhang, Qinghao Mori, Tatsunori |
| contents | The Mutual Reinforcement Effect (MRE) investigates the synergistic relationship between word-level and text-level classifications in text classification tasks. It posits that the performance of both classification levels can be mutually enhanced. However, this mechanism has not been adequately demonstrated or explained in prior research. To address this gap, we employ information flow analysis to observe and substantiate the MRE theory. Our experiments on six MRE hybrid datasets revealed the presence of MRE in the model and its impact. Additionally, we conducted fine-tuning experiments, whose results were consistent with those of the information flow experiments. The convergence of findings from both experiments corroborates the existence of MRE. Furthermore, we extended the application of MRE to prompt learning, utilizing word-level information as a verbalizer to bolster the model's prediction of text-level classification labels. In our final experiment, the F1-score significantly surpassed the baseline in five out of six datasets, further validating the notion that word-level information enhances the language model's comprehension of the text as a whole. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_02902 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Demonstrating Mutual Reinforcement Effect through Information Flow Gan, Chengguang He, Xuzheng Zhang, Qinghao Mori, Tatsunori Computation and Language The Mutual Reinforcement Effect (MRE) investigates the synergistic relationship between word-level and text-level classifications in text classification tasks. It posits that the performance of both classification levels can be mutually enhanced. However, this mechanism has not been adequately demonstrated or explained in prior research. To address this gap, we employ information flow analysis to observe and substantiate the MRE theory. Our experiments on six MRE hybrid datasets revealed the presence of MRE in the model and its impact. Additionally, we conducted fine-tuning experiments, whose results were consistent with those of the information flow experiments. The convergence of findings from both experiments corroborates the existence of MRE. Furthermore, we extended the application of MRE to prompt learning, utilizing word-level information as a verbalizer to bolster the model's prediction of text-level classification labels. In our final experiment, the F1-score significantly surpassed the baseline in five out of six datasets, further validating the notion that word-level information enhances the language model's comprehension of the text as a whole. |
| title | Demonstrating Mutual Reinforcement Effect through Information Flow |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.02902 |