SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.16155 · NAACL · 2024

Improving Multi-lingual Alignment Through Soft Contrastive Learning

Jy-Yong Sohn, Chanyeol Choi, Minsu Park, Seyeon Choi

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 6 failures 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/2405.16155.json · badge: /api/ran/2405.16155.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
yai12xlinq-b/imascl canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
AMEMetric Ran
ran; our contract draft was wrong, not the code
yai12xlinq-b/imascl/modules/AMEMetric.py
pointer only (licence: NONE) · get_code("f2eb30d40c460710")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yai12xlinq-b/imascl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_sim_matrix Ran
ran, honoured the contract we drafted
yai12xlinq-b/imascl/evaluate/make_sim_matrix.py
pointer only (licence: NONE) · get_code("63718959cc46f0ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yai12xlinq-b/imascl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

encode Ran
ran; our contract draft was wrong, not the code
yai12xlinq-b/imascl/evaluate/make_sim_matrix.py
pointer only (licence: NONE) · get_code("619b6842fb1a677c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yai12xlinq-b/imascl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_length_in_batch_grouped_indices Ran
ran; our contract draft was wrong, not the code
yai12xlinq-b/imascl/modules/AMESampler.py
pointer only (licence: NONE) · get_code("ce814733ea98b647")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yai12xlinq-b/imascl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_length_in_batch_grouped_indices_idx_dict Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yai12xlinq-b/imascl/modules/AMESampler.py
pointer only (licence: NONE) · get_code("ce4c548f1e2d2c28")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yai12xlinq-b/imascl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

has_length Ran
ran on a synthesized input
yai12xlinq-b/imascl/modules/AMETrainer.py
pointer only (licence: NONE) · get_code("fc0516e02c0038d1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yai12xlinq-b/imascl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_score Ran
ran, honoured the contract we drafted
yai12xlinq-b/imascl/utils/result_parse.py
pointer only (licence: NONE) · get_code("ce93adc6cc1fd151")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yai12xlinq-b/imascl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

move_to_cuda Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yai12xlinq-b/imascl/evaluate/run_mteb.py
pointer only (licence: NONE) · get_code("ec34b8cf0146fcf2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yai12xlinq-b/imascl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

torch_AME_data_collator Ran
ran; our contract draft was wrong, not the code
yai12xlinq-b/imascl/modules/AMEDataCollator.py
pointer only (licence: NONE) · get_code("45fcc53eef1da47d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yai12xlinq-b/imascl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

tatoeba_filtering Not yet run
unverified (harvested, no recorded run)
yai12xlinq-b/imascl/utils/filter_tatoeba.py
pointer only (licence: NONE) · get_code("fcb720034daff71a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yai12xlinq-b/imascl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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
has_length 1 other paper
1 dated earlier
2402.16829 (2024-02)
GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning

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

Making decent multi-lingual sentence representations is critical to achieve high performances in cross-lingual downstream tasks. In this work, we propose a novel method to align multi-lingual embeddings based on the similarity of sentences measured by a pre-trained mono-lingual embedding model. Given translation sentence pairs, we train a multi-lingual model in a way that the similarity between cross-lingual embeddings follows the similarity of sentences measured at the mono-lingual teacher model. Our method can be considered as contrastive learning with soft labels defined as the similarity between sentences. Our experimental results on five languages show that our contrastive loss with soft labels far outperforms conventional contrastive loss with hard labels in various benchmarks for bitext mining tasks and STS tasks. In addition, our method outperforms existing multi-lingual embeddings including LaBSE, for Tatoeba dataset. The code is available at https://github.com/ YAI12xLinq-B/IMASCL

For agents

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

get_harvested_code_for_paper("2405.16155")
get_code_for_paper("2405.16155")
have("2405.16155")

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

curl https://syntology.ai/api/ran/2405.16155.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.16155.svg)](https://syntology.ai/paper/2405.16155)

Connect an agent — have() is free.