Papers by Si-An Chen

4 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations