Decomposable Attention
2016Attention model that decomposes the problem of comparing two sentences into aligning and comparing sub-phrases using only feed-forward attention, with no recurrence (Parikh, Tackstrom, Das & Uszkoreit, "A Decomposable Attention Model," EMNLP 2016). One of the few pre-Transformer models to rely on attention without a recurrent network, cited by Vaswani et al. as a direct precedent for dispensing with recurrence entirely.
Originators
- Parikh, A.
- Tackstrom, O.
- Das, D.
- Uszkoreit, J.
Landmark Paper
Checked 2026-09-19 — interim signal only, see docs/BASIC_ROADMAP.md Phase 10
Connections
- is precursor to Transformerbasis: reasoned
Vaswani et al. cite Parikh et al.'s Decomposable Attention (ref [27], their own footnote "in all but a few cases [27]") as the direct precedent showing attention alone -- without recurrence -- could carry a transduction task; the Transformer generalizes this to self-attention with multi-head projection and positional encoding.