MATE

2000년 도입 · 논문 14편에서 사용

MATE is a Transformer architecture designed to model the structure of web tables. It uses sparse attention in a way that allows heads to efficiently attend to either rows or columns in a table. Each attention head reorders the tokens by either column or row index and then applies a windowed attention mechanism. Unlike traditional self-attention, Mate scales linearly in the sequence length.

출처: MATE: Multi-view Attention for Table Transformer Efficiency

소개 논문: MATE: Multi-view Attention for Table Transformer Efficiency