CoChat

The sequence memoizer

Wood, Frank, Gasthaus, Jan, Archambeau, Cédric, James, Lancelot, Teh, Yee Whye · 2011 · Communications of the ACM
Cited by 51

The DOI matches its Crossref record.

Abstract

Probabilistic models of sequences play a central role in most machine translation, automated speech recognition, lossless compression, spell-checking, and gene identification applications to name but a few. Unfortunately, real-world sequence data often exhibit long range dependencies which can only be captured by computationally challenging, complex models. Sequence data arising from natural processes also often exhibits power-law properties, yet common sequence models do not capture such properties. The sequence memoizer is a new hierarchical Bayesian model for discrete sequence data that captures long range dependencies and power-law characteristics, while remaining computationally attractive. Its utility as a language model and general purpose lossless compressor is demonstrated.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/1897816.1897842

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cited by

  • “It turns out that some of the world’s best compression algorithms (for example, Sequence Memoizer 79 and PPM with dynamic parameter updates 80 ) are equivalent to Bayesian non-parametric models of sequences, and improvements to compression are being made through a better understanding of how to…”
    Method
  • Temporal Sequence Modeling for Video Event Detection

    Cheng, Y., Fan, Q., Pankanti, S., & Choudhary, A. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.286 · Cited by 80

    “Addressing such long contexts is a valid concern in previous work [22].”
    BackgroundMethod
  • Learning higher-order sequential structure with cloned HMMs

    Dedieu, A., Gothoskar, N., Swingle, S., Lehrach, W., Lázaro-Gredilla, M., & George, D. (2019) · arXiv · doi:10.48550/arxiv.1905.00507 · Cited by 7

    “When a predictive context contains “holes” of irrelevant symbols 1 that do not affect prediction, n-grams and sequence memoizers [26] will need exponentially (in the number of holes) more training data to be able to use the context for prediction, whereas CHMMs can handle such sequences efficiently…”
    BackgroundMethodInfluential

See all 51

Metadata

Authors
Wood, F., Gasthaus, J., Archambeau, C., James, L., & Teh, Y. W.
Venue
Communications of the ACM
Published
2011-02
Volume
54
Issue
2
Pages
91-98
ISSN
  • 0001-0782 (ISSN-L)
  • 1557-7317
OpenAlex
W2057147815
Cited by
51
References
0
FWCI
6.21
Type
journal article
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: The sequence memoizer. https://app.cochat.ai/papers/10.1145/1897816.1897842
The paper
Wood, F., Gasthaus, J., Archambeau, C., James, L., & Teh, Y. W. (2011). The sequence memoizer. Communications of the ACM. https://doi.org/10.1145/1897816.1897842

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.