Skip to content
AI News HubLIVE
Original source2 min read

khammoon: From a Linguistic Guideline to a Thai Morpheme Segmenter

Summary

Thai researchers propose segmenting Thai at the morpheme (khammoon) level rather than the word level to eliminate compounding ambiguity. They create a formal guideline with near-perfect human agreement, scale annotation with an LLM, and train a 1M-parameter convolutional BiLSTM segmenter that achieves 0.992 boundary F1 on out-of-domain text while maintaining or exceeding word-level baselines on downstream tasks.

SourcearXiv Computational LinguisticsAuthor: Warit Sirichotedumrong, Adisai Na-Thalang, Chanakan Wittayasakpan, Kritsadha Phatcharoen, Kunat Pipatanakul
khammoon: From a Linguistic Guideline to a Thai Morpheme Segmenter
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 9 Nov 2026]

Title:khammoon: From a Linguistic Guideline to a Thai Morpheme Segmenter

View a PDF of the paper titled khammoon: From a Linguistic Guideline to a Thai Morpheme Segmenter, by Warit Sirichotedumrong and 4 other authors

View PDF HTML (experimental)

Abstract:Thai is written without spaces between words, making segmentation a foundational step in most Thai NLP pipelines. Existing tools primarily reproduce the word-level conventions of corpora such as BEST; however, because the notion of a "word" in Thai lacks a unified linguistic consensus, these conventions struggle with productive compounding, leading to arbitrary boundaries and ambiguity in downstream representations. Instead, we propose operating at the morphological level, focusing on khammoon, the smallest atomic unit that carries meaning. Segmenting at the morphemic level provides an explicit, consistent morphological representation that eliminates compounding ambiguity. Crucially, this representation benefits downstream learning: models trained on morphemes perform on par with or exceed word-level baselines across part-of-speech tagging, named-entity recognition, and sentiment classification, demonstrating that linguistic consistency improves representation quality without downstream performance penalty. To operationalize this representation, we translate linguistic principles into a formal decision guideline with near-perfect human agreement ($\kappa \approx 0.99$), scale annotation with an LLM, and correct systematic errors with human labels. Finally, we train khammoon, a lightweight 1M-parameter convolutional BiLSTM segmenter designed for efficient CPU inference, achieving a boundary F1 of 0.992 on out-of-domain text. The guideline, datasets, model, and library are all publicly released.

Comments: Technical Report. Code, models, and data are available at this https URL

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2611.13012 [cs.CL]

(or arXiv:2611.13012v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.13012

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Warit Sirichotedumrong [view email] [v1] Mon, 9 Nov 2026 03:19:53 UTC (3,539 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled khammoon: From a Linguistic Guideline to a Thai Morpheme Segmenter, by Warit Sirichotedumrong and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CL

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Thai lacks spaces and a unified definition of 'word', causing arbitrary boundaries in productive compounding.
  • Morpheme-level segmentation (khammoon) provides explicit, consistent representations without downstream performance loss.
  • Annotation guideline achieves κ≈0.99 human agreement; LLM scaling with human correction builds the dataset.
  • Lightweight 1M-parameter BiLSTM segmenter runs efficiently on CPU with 0.992 boundary F1 out-of-domain.

Highlights and analysis are generated automatically and may contain errors. Check the original source.