A Debiased Nearest Neighbors Framework for Multi-Label Text Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909280621297664 |
|---|---|
| author | Cheng, Zifeng Jiang, Zhiwei Yin, Yafeng Chen, Zhaoling Wang, Cong Ge, Shiping Huang, Qiguo Gu, Qing |
| author_facet | Cheng, Zifeng Jiang, Zhiwei Yin, Yafeng Chen, Zhaoling Wang, Cong Ge, Shiping Huang, Qiguo Gu, Qing |
| contents | Multi-Label Text Classification (MLTC) is a practical yet challenging task that involves assigning multiple non-exclusive labels to each document. Previous studies primarily focus on capturing label correlations to assist label prediction by introducing special labeling schemes, designing specific model structures, or adding auxiliary tasks. Recently, the $k$ Nearest Neighbor ($k$NN) framework has shown promise by retrieving labeled samples as references to mine label co-occurrence information in the embedding space. However, two critical biases, namely embedding alignment bias and confidence estimation bias, are often overlooked, adversely affecting prediction performance. In this paper, we introduce a DEbiased Nearest Neighbors (DENN) framework for MLTC, specifically designed to mitigate these biases. To address embedding alignment bias, we propose a debiased contrastive learning strategy, enhancing neighbor consistency on label co-occurrence. For confidence estimation bias, we present a debiased confidence estimation strategy, improving the adaptive combination of predictions from $k$NN and inductive binary classifications. Extensive experiments conducted on four public benchmark datasets (i.e., AAPD, RCV1-V2, Amazon-531, and EUR-LEX57K) showcase the effectiveness of our proposed method. Besides, our method does not introduce any extra parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_03202 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Debiased Nearest Neighbors Framework for Multi-Label Text Classification Cheng, Zifeng Jiang, Zhiwei Yin, Yafeng Chen, Zhaoling Wang, Cong Ge, Shiping Huang, Qiguo Gu, Qing Computation and Language Multi-Label Text Classification (MLTC) is a practical yet challenging task that involves assigning multiple non-exclusive labels to each document. Previous studies primarily focus on capturing label correlations to assist label prediction by introducing special labeling schemes, designing specific model structures, or adding auxiliary tasks. Recently, the $k$ Nearest Neighbor ($k$NN) framework has shown promise by retrieving labeled samples as references to mine label co-occurrence information in the embedding space. However, two critical biases, namely embedding alignment bias and confidence estimation bias, are often overlooked, adversely affecting prediction performance. In this paper, we introduce a DEbiased Nearest Neighbors (DENN) framework for MLTC, specifically designed to mitigate these biases. To address embedding alignment bias, we propose a debiased contrastive learning strategy, enhancing neighbor consistency on label co-occurrence. For confidence estimation bias, we present a debiased confidence estimation strategy, improving the adaptive combination of predictions from $k$NN and inductive binary classifications. Extensive experiments conducted on four public benchmark datasets (i.e., AAPD, RCV1-V2, Amazon-531, and EUR-LEX57K) showcase the effectiveness of our proposed method. Besides, our method does not introduce any extra parameters. |
| title | A Debiased Nearest Neighbors Framework for Multi-Label Text Classification |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.03202 |