Demonstrating Mutual Reinforcement Effect through Information Flow
This work addresses a gap in understanding synergistic relationships in text classification for researchers, though it appears incremental as it focuses on demonstrating an existing theory.
The paper tackled the problem of demonstrating and explaining the Mutual Reinforcement Effect (MRE) in text classification by using information flow analysis and fine-tuning experiments, showing that word-level and text-level classifications can mutually enhance performance, with F1-scores significantly surpassing baselines in five out of six datasets.
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.