Papers by Si-An Chen
Preserving Zero-shot Capability in Supervised Fine-tuning for Multi-label Text Classification (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods that assume label descriptions ensure zero-shot capability lose their zero-shot capability during training. |
| Approach: | They propose a method that preserves the zero-shot capabilities of powerful dual encoders and label-wise attention networks by freezing the label encoder. |
| Outcome: | The proposed methods preserve the zero-shot capabilities of powerful dual encoder and label-wise attention network architectures by freezing the label encoder. |
Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNN (2022.naacl-main)
Copied to clipboard
| Challenge: | XML-CNN has been a popular research topic in NLP due to its superior performance . however, the increasing complexity brings difficulties to ensure the true architectural progress . |
| Approach: | They propose to re-examine an influential multi-label text classification method . they propose suitable baselines for multi-level text classification tasks . |
| Outcome: | The proposed method performs better than the original model, the authors show . they show that the re-implementation reveals contradictory results to the original work . |
Parameter Selection: Why We Should Pay More Attention to It (2021.acl-short)
Copied to clipboard
| Challenge: | supervised learning is a challenging process due to the huge number of parameter combinations. |
| Approach: | They present an example of parameter selection in supervised learning . authors use a set of frequently occurring labels without a parameter tuning . they say this illustrates the seriousness of parameter tuning in a supervised field . |
| Outcome: | The proposed study shows that without adequate attention, the research progress can be uncertain or even illusive. |
Linear Classifier: An Often-Forgotten Baseline for Text Classification (2023.acl-short)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models such as BERT are popular solutions for text classification. |
| Approach: | They argue that large-scale pre-trained language models such as BERT are popular solutions for text classification . authors argue that running a simple baseline like linear classifiers on bag-of-words features is important for text classification . |
| Outcome: | The proposed approach may only sometimes get satisfactory results for some problems. |