AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Intermediate N-Gramming: Deterministic and Fast N-Grams for Large N and Large Datasets

Ryan R. Curtin, Fred Lu, Edward Raff, Priyanka Ranade

AAAI 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Constrained neural network optimization · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace hash-gramming (hg-fast) with Intergrams z=1top-k n-gram mining · C4 (k=10k)runtime (s): 30811.2s -> 1183.9sImproved
replace hg-fast with Intergrams z=1top-k n-gram mining · EMBER (k=100k)runtime (s): 7162.6s -> 1413.7sImproved
replace hg-fast with Intergrams z=1top-k n-gram mining · 1000gp (k=10k)runtime (s): 7061.5s -> 1215.7sImproved
increase oversampling z from 1 to 1.5 (ablation)Intergrams · EMBER (k=100k)Jaccard with true top-k: 0.71 -> 0.91Improved
increase oversampling z from 1.5 to 2 (ablation)Intergrams · EMBER (k=100k)Jaccard with true top-k: 0.91 -> 0.97Improved
increase oversampling z from 1 to 2 (ablation)Intergrams · EMBER (k=100k)speedup: 6.42x -> 5.13xHurt
increase oversampling z from 1 to 1.5 (ablation)Intergrams · C4 (k=10k)Jaccard with true top-k: 0.91 -> 1.0Improved
increase oversampling z from 1 to 2 (ablation)Intergrams · C4 (k=10k)speedup: 33.6x -> 26.5xHurt
increase oversampling z from 1 to 2 (ablation)Intergrams · 1000gp (k=10k)Jaccard with true top-k: 1.0No clear effect
add 2 MB large pages to hash-gramming (ablation)hg-vanilla · EMBER (k=100k)speedup: 1.01x -> 1.08xImproved
add cuckoo hashing and other cumulative tricks to hash-gramming (ablation)hg-vanilla · C4 (k=10k)speedup: 1.01x -> 1.06x (hg-cuckoo), 1.29x (hg-fast)Improved
use trie for exact-count pass in hash-gramming (ablation)hash-gramming · 1000gp (k=10k)speedup: 1.16x -> 1.24xImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy