PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead

no code implementations • 29 Sep 2024 • Tao Tan, Yining Qian, Ang Lv, Hongzhan Lin, Songhao Wu, Yongbo Wang, Feng Wang, Jingtong Wu, Xin Lu, Rui Yan

During inference, the optimized coefficients are fixed to re-weight these heads, regardless of the specific task at hand.

Position RAG +1

Relation Aware Semi-autoregressive Semantic Parsing for NL2SQL

no code implementations • 2 Aug 2021 • Junyang Huang, Yongbo Wang, Yongliang Wang, Yang Dong, Yanghua Xiao

It first learns relation embedding over the schema entities and question words with predefined schema relations with ELECTRA and relation aware transformer layer as backbone.

Relation Semantic Parsing

SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising

1 code implementation • Findings (NAACL) 2022 • Kuan Xu, Yongbo Wang, Yongliang Wang, Zujie Wen, Yang Dong

In text-to-SQL task, seq-to-seq models often lead to sub-optimal performance due to limitations in their architecture.

Decoder Denoising +3

NAIRS: A Neural Attentive Interpretable Recommendation System

no code implementations • 20 Feb 2019 • Shuai Yu, Yongbo Wang, Min Yang, Baocheng Li, Qiang Qu, Jialie Shen

In this paper, we develop a neural attentive interpretable recommendation system, named NAIRS.