MATE: Multi-view Attention for Table Transformer Efficiency
This addresses the problem of efficiently processing large web tables for AI applications, representing an incremental advance in domain-specific model design.
The paper tackles the challenge of modeling large tables in documents with Transformer models, which are typically limited to 512 tokens, by proposing MATE, a sparse-attention Transformer architecture that scales linearly and sets a new state-of-the-art, improving the best prior result on HybridQA by 19 points.
This work presents a sparse-attention Transformer architecture for modeling documents that contain large tables. Tables are ubiquitous on the web, and are rich in information. However, more than 20% of relational tables on the web have 20 or more rows (Cafarella et al., 2008), and these large tables present a challenge for current Transformer models, which are typically limited to 512 tokens. Here we propose MATE, a novel Transformer architecture designed to model the structure of web tables. MATE uses sparse attention in a way that allows heads to efficiently attend to either rows or columns in a table. This architecture scales linearly with respect to speed and memory, and can handle documents containing more than 8000 tokens with current accelerators. MATE also has a more appropriate inductive bias for tabular data, and sets a new state-of-the-art for three table reasoning datasets. For HybridQA (Chen et al., 2020b), a dataset that involves large documents containing tables, we improve the best prior result by 19 points.