Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.17534 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909233963859968 |
|---|---|
| author | Chen, Huiyao Zhao, Yu Chen, Zulong Wang, Mengjia Li, Liangyue Zhang, Meishan Zhang, Min |
| author_facet | Chen, Huiyao Zhao, Yu Chen, Zulong Wang, Mengjia Li, Liangyue Zhang, Meishan Zhang, Min |
| contents | Hierarchical text classification (HTC) is an important task with broad applications, while few-shot HTC has gained increasing interest recently. While in-context learning (ICL) with large language models (LLMs) has achieved significant success in few-shot learning, it is not as effective for HTC because of the expansive hierarchical label sets and extremely-ambiguous labels. In this work, we introduce the first ICL-based framework with LLM for few-shot HTC. We exploit a retrieval database to identify relevant demonstrations, and an iterative policy to manage multi-layer hierarchical labels. Particularly, we equip the retrieval database with HTC label-aware representations for the input texts, which is achieved by continual training on a pretrained language model with masked language modeling (MLM), layer-wise classification (CLS, specifically for HTC), and a novel divergent contrastive learning (DCL, mainly for adjacent semantically-similar labels) objective. Experimental results on three benchmark datasets demonstrate superior performance of our method, and we can achieve state-of-the-art results in few-shot HTC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17534 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification Chen, Huiyao Zhao, Yu Chen, Zulong Wang, Mengjia Li, Liangyue Zhang, Meishan Zhang, Min Computation and Language Hierarchical text classification (HTC) is an important task with broad applications, while few-shot HTC has gained increasing interest recently. While in-context learning (ICL) with large language models (LLMs) has achieved significant success in few-shot learning, it is not as effective for HTC because of the expansive hierarchical label sets and extremely-ambiguous labels. In this work, we introduce the first ICL-based framework with LLM for few-shot HTC. We exploit a retrieval database to identify relevant demonstrations, and an iterative policy to manage multi-layer hierarchical labels. Particularly, we equip the retrieval database with HTC label-aware representations for the input texts, which is achieved by continual training on a pretrained language model with masked language modeling (MLM), layer-wise classification (CLS, specifically for HTC), and a novel divergent contrastive learning (DCL, mainly for adjacent semantically-similar labels) objective. Experimental results on three benchmark datasets demonstrate superior performance of our method, and we can achieve state-of-the-art results in few-shot HTC. |
| title | Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.17534 |