Papers by Chun Lin
Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent Chinese word segmentation models tend to learn the segmentation knowledge through in-vocabulary words rather than understanding the meaning of the entire context. |
| Approach: | They propose a context-aware approach that incorporates unsupervised sentence representation learning over different dropout masks into the multi-criteria training framework. |
| Outcome: | The proposed approach achieves state-of-the-art (SoTA) performance on six of the nine CWS benchmark datasets and out-of vocabulary (OOV) recalls for eight of nine. |
Improved Unsupervised Chinese Word Segmentation Using Pre-trained Knowledge and Pseudo-labeling Transfer (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to unsupervised Chinese word segmentation require multiple inferences to perform word segmenting. |
| Approach: | They propose a method that integrates the segmentation signal from an unsupervised language model to a pre-trained BERT classifier under a pseudo-labeling framework. |
| Outcome: | The proposed method achieves state-of-the-art performance on the eight UCWS tasks while significantly reducing training time compared to previous approaches. |
IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing quantization methods are compromising performance of large language models (LLMs) despite their high computational intensity, LLMs are still demanding intensive computation. |
| Approach: | They propose to generate the KV cache of pivot tokens losslessly from the full-precision model. |
| Outcome: | The proposed method generates the KV cache of pivot tokens losslessly from the full-precision model with no extra inference overhead. |