Ching Yang


2023

pdf
Breaking Boundaries in Retrieval Systems: Unsupervised Domain Adaptation with Denoise-Finetuning
Che Chen | Ching Yang | Chun-Yi Lin | Hung-Yu Kao
Findings of the Association for Computational Linguistics: EMNLP 2023

Dense retrieval models have exhibited remarkable effectiveness, but they rely on abundant labeled data and face challenges when applied to different domains. Previous domain adaptation methods have employed generative models to generate pseudo queries, creating pseudo datasets to enhance the performance of dense retrieval models. However, these approaches typically use unadapted rerank models, leading to potentially imprecise labels. In this paper, we demonstrate the significance of adapting the rerank model to the target domain prior to utilizing it for label generation. This adaptation process enables us to obtain more accurate labels, thereby improving the overall performance of the dense retrieval model. Additionally, by combining the adapted retrieval model with the adapted rerank model, we achieve significantly better domain adaptation results across three retrieval datasets. We release our code for future research.

pdf
Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation
Chun Lin | Ying-Jia Lin | Chia-Jen Yeh | Yi-Ting Li | Ching Yang | Hung-Yu Kao
Findings of the Association for Computational Linguistics: EMNLP 2023

Recent Chinese word segmentation (CWS) models have shown competitive performance with pre-trained language models’ knowledge. However, these models tend to learn the segmentation knowledge through in-vocabulary words rather than understanding the meaning of the entire context. To address this issue, we introduce a context-aware approach that incorporates unsupervised sentence representation learning over different dropout masks into the multi-criteria training framework. We demonstrate that our approach reaches state-of-the-art (SoTA) performance on F1 scores for six of the nine CWS benchmark datasets and out-of-vocabulary (OOV) recalls for eight of nine. Further experiments discover that substantial improvements can be brought with various sentence representation objectives.