Xiaohua Li


2022

pdf bib
Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder
Zhenghao Liu | Han Zhang | Chenyan Xiong | Zhiyuan Liu | Yu Gu | Xiaohua Li
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Dense retrievers encode queries and documents and map them in an embedding space using pre-trained language models. These embeddings need to be high-dimensional to fit training signals and guarantee the retrieval effectiveness of dense retrievers. However, these high-dimensional embeddings lead to larger index storage and higher retrieval latency. To reduce the embedding dimensions of dense retrieval, this paper proposes a Conditional Autoencoder (ConAE) to compress the high-dimensional embeddings to maintain the same embedding distribution and better recover the ranking features. Our experiments show that ConAE is effective in compressing embeddings by achieving comparable ranking performance with its teacher model and making the retrieval system more efficient. Our further analyses show that ConAE can alleviate the redundancy of the embeddings of dense retrieval with only one linear layer. All codes of this work are available at https://github.com/NEUIR/ConAE.

2006

pdf bib
Statistical Survey of Monophthong Formants in Mandarin for Students Being Trained as Broadcasters
Zihou Meng | Yudong Chen | Xiaohua Li
Proceedings of the 20th Pacific Asia Conference on Language, Information and Computation