Skip to content
conftrace_

self-attention model

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

least square (1) data pipeline (1) multi-head self-attention (1) multi-head attention (1) masked language modeling (1) pivot language (1) pivot translation (1) pseudo-parallel corpus (1) subword segmentation (1) attention sink (1)

Papers

Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks ACL 2026 On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability NeurIPS 2024 Unsupervised Dependency Graph Network ACL 2022 Detect Profane Language in Streaming Services to Protect Young Audiences ACL 2021 The TALP-UPC Machine Translation Systems for WMT19 News Translation Task: Pivoting Techniques for Low Resource MT ACL 2019