Methods › General › Structured Prediction › CRF

Conditional Random Field

CRF

468 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is modeled as a graphical model, which implements dependencies between the predictions. Graph choice depends on the application, for example linear chain CRFs are popular in natural language processing, whereas in image-based tasks, the graph would connect to neighboring locations in an image to enforce that they have similar predictions.

Image Credit: Charles Sutton and Andrew McCallum, An Introduction to Conditional Random Fields

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: CRF-AE; DS-CRF; DSSM-CRF; Gumbel-CRF; CRF-filling; CRF-LightGBM system; two-stage CRF parser; Neural CRF alignment model.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 468 · with a code link: 159 · where Syntology ran a sample: 20 (19 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (20 of 468 tagged: 19 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 5: papers 1 to 100 of 468, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 348 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Semantic Segmentation103
Segmentation90
Named Entity Recognition (NER)67
Named Entity Recognition64
named-entity-recognition62
NER47
Image Segmentation38
Sentence30
Word Embeddings27
General Classification23
POS21
object-detection20
Object Detection19
Part-Of-Speech Tagging18
Object16
POS Tagging14
Structured Prediction14
TAG14
Language Modelling13
Machine Translation13

Usage over time archive 2025-07-28

Papers per year tagged with CRF: 2008 to 2025, peak 73 73 0 2008: 1 paper 2008 2009: 1 paper 2010: 0 papers 2010 2011: 0 papers 2012: 2 papers 2012 2013: 2 papers 2014: 11 papers 2014 2015: 22 papers 2016: 46 papers 2016 2017: 54 papers 2018: 70 papers 2018 2019: 63 papers 2020: 73 papers 2020 2021: 43 papers 2022: 30 papers 2022 2023: 23 papers 2024: 15 papers 2024 2025: 12 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (468 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Structured Prediction

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections