Methods › Natural Language Processing › Subword Segmentation › Unigram Segmentation
Unigram Segmentation
Introduced by Taku Kudo in Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Unigram Segmentation is a subword segmentation algorithm based on a unigram language model. It provides multiple segmentations with probabilities. The language model allows for emulating the noise generated during the segmentation of actual data.
The unigram language model makes an assumption that each subword occurs independently, and consequently, the probability of a subword sequence x = (x₁,…,x_M) is formulated as the product of the subword occurrence probabilities p(xᵢ):
P(x) = ∏ᵢ₌₁ᴹ p(xᵢ), ∀i xᵢ ∈𝒱, ∑_(x ∈𝒱) p(x) = 1,
where 𝒱 is a pre-determined vocabulary. The most probable segmentation x^* for the input sentence X is then given by:
x^* = argmax_(x ∈𝒮(X)) P(x),
where 𝒮(X) is a set of segmentation candidates built from the input sentence X. x^* is obtained with the Viterbi algorithm.
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: Model Segmentation; Play Segmentation (PS); Latent Noise Segmentation; zero-guidance segmentation; simple segmentation method; Quantum Motion Segmentation; Amodal Panoptic Segmentation; real-time segmentation 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: 1 · with a code link: 0 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 1 tagged papers has a Syntology run on record
Page 1 of 1: paper 1 of 1, 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.
-
Benchmarking Azerbaijani Neural Machine Translation 29 Jul 2022 · 0 repositories · arXiv:2207.14473
Tasks archive 2025-07-28
6 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Benchmarking | 1 |
| Domain Generalization | 1 |
| Machine Translation | 1 |
| NMT | 1 |
| Segmentation | 1 |
| Translation | 1 |
Usage over time archive 2025-07-28
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
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