Demonstrating Mutual Reinforcement Effect through Information Flow

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gan, Chengguang, He, Xuzheng, Zhang, Qinghao, Mori, Tatsunori
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