SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.04679 · 2023

Embedding structure matters: Comparing methods to adapt multilingual vocabularies to new languages

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2309.04679.json · badge: /api/ran/2309.04679.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
cmdowney88/embeddingstructure canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
hex2dec Ran
ran, honoured the contract we drafted
cmdowney88/embeddingstructure/src/reinitialize_embeddings.py
code served (permissive licence) · get_code("74b4020b7c03984e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

# The function hex2dec takes a hexadecimal string and converts it to decimal
# It only requires one parameter: hex_str, which should be a string

ARGS = {
    "hex_str": "1A"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
top_script Ran
ran; our contract draft was wrong, not the code
cmdowney88/embeddingstructure/src/reinitialize_embeddings.py
code served (permissive licence) · get_code("8e6d49aaf98611d9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from collections import defaultdict

# Create a simple mapping from character ordinals to script names
ord2script = {
    ord('a'): 'latin',
    ord('b'): 'latin',
    ord('c'): 'latin',
    ord('α'): 'greek',
    ord('β'): 'greek',
    ord('中'): 'cjk',
    ord('文'): 'cjk',
}

token = "abcαβ中"

ARGS = {
    'token': token,
    'ord2script': ord2script,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_ord2script Not yet run
unverified (harvested, no recorded run)
cmdowney88/embeddingstructure/src/reinitialize_embeddings.py
code served (permissive licence) · get_code("e8e4a9db7236b331")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_ord2script 2 other papers
2 later
2024.findings-emnlp.918 (2024 (year only))
Targeted Multilingual Adaptation for Low-resource Language Families
2408.15793 (2024-08)
Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough
hex2dec 2 other papers
2 later
2024.findings-emnlp.918 (2024 (year only))
Targeted Multilingual Adaptation for Low-resource Language Families
2408.15793 (2024-08)
Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough
top_script 2 other papers
2 later
2024.findings-emnlp.918 (2024 (year only))
Targeted Multilingual Adaptation for Low-resource Language Families
2408.15793 (2024-08)
Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Pre-trained multilingual language models underpin a large portion of modern NLP tools outside of English. A strong baseline for specializing these models for specific languages is Language-Adaptive Pre-Training (LAPT). However, retaining a large cross-lingual vocabulary and embedding matrix comes at considerable excess computational cost during adaptation. In this study, we propose several simple techniques to replace a cross-lingual vocabulary with a compact, language-specific one. Namely, we address strategies for re-initializing the token embedding matrix after vocabulary specialization. We then provide a systematic experimental comparison of our techniques, in addition to the recently-proposed Focus method. We demonstrate that: 1) Embedding-replacement techniques in the monolingual transfer literature are inadequate for adapting multilingual models. 2) Replacing cross-lingual vocabularies with smaller specialized ones provides an efficient method to improve performance in low-resource languages. 3) Simple embedding re-initialization techniques based on script-wise sub-distributions rival techniques such as Focus, which rely on similarity scores obtained from an auxiliary model.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2309.04679")
get_code_for_paper("2309.04679")
have("2309.04679")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2309.04679.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2309.04679.svg)](https://syntology.ai/paper/2309.04679)

Connect an agent — have() is free.