SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.09433 · NeurIPS · 2022

Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings

Chongyang Gao, Soroush Vosoughi, Yiren Jian

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2209.09433.json · badge: /api/ran/2209.09433.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
yiren-jian/NonLing-CSE marked official in Papers with Code
Papers with Code archive
5 ran · 3 no recorded run
FunctionStatusWhere it lives
PatchEmbed Ran
ran on a synthesized input · constructed an object; no result was computed
yiren-jian/NonLing-CSE/AudioCSE/src/models.py
pointer only (licence: NONE) · get_code("6dde63220b0a3882")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yiren-jian/NonLing-CSE 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.

Pooler Ran
ran on a synthesized input · constructed an object; no result was computed
yiren-jian/NonLing-CSE/AudioCSE/src/models.py
pointer only (licence: NONE) · get_code("31695b3bea2d46ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yiren-jian/NonLing-CSE 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.

Similarity Ran
ran on a synthesized input · constructed an object; no result was computed
yiren-jian/NonLing-CSE/AudioCSE/src/models.py
pointer only (licence: NONE) · get_code("4d41003f996241f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yiren-jian/NonLing-CSE 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.

cl_forward Ran
ran; our contract draft was wrong, not the code
yiren-jian/NonLing-CSE/AudioCSE/src/models.py
pointer only (licence: NONE) · get_code("4e0ff9c4d9a318ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yiren-jian/NonLing-CSE 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.

sentemb_forward Ran
ran; our contract draft was wrong, not the code
yiren-jian/NonLing-CSE/AudioCSE/src/models.py
pointer only (licence: NONE) · get_code("cb67cd5ac977480d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yiren-jian/NonLing-CSE 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.

BertForCL Not yet run
unverified (harvested, no recorded run)
yiren-jian/NonLing-CSE/AudioCSE/src/models.py
pointer only (licence: NONE) · get_code("cac05caf11e54d56")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yiren-jian/NonLing-CSE 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.

MLPLayer Not yet run
unverified (harvested, no recorded run)
yiren-jian/NonLing-CSE/AudioCSE/src/models.py
pointer only (licence: NONE) · get_code("7d7789da5378c84b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yiren-jian/NonLing-CSE 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.

cl_init Not yet run
unverified (harvested, no recorded run)
yiren-jian/NonLing-CSE/AudioCSE/src/models.py
pointer only (licence: NONE) · get_code("0e3742a153290ee6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yiren-jian/NonLing-CSE 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 5 later) and 3 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
sentemb_forward
brick of this paper's assembly: model
15 other papers
4 dated earlier, 11 later · 4 only as an assembly brick
1908.10084 (2019-08)
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
2104.08821 (2021-04)
SimCSE: Simple Contrastive Learning of Sentence Embeddings
2203.05877 (2022-03)
A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings
and 12 more not named here
Similarity
brick of this paper's assembly: model
12 other papers
9 dated earlier, 3 later · 12 only as an assembly brick
1907.11692 (2019-07)
RoBERTa: A Robustly Optimized BERT Pretraining Approach
1908.10084 (2019-08)
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
2010.01057 (2020-10)
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
and 9 more not named here
MLPLayer
brick of this paper's assembly: model
9 other papers
7 dated earlier, 2 later · 9 only as an assembly brick
1907.11692 (2019-07)
RoBERTa: A Robustly Optimized BERT Pretraining Approach
1908.10084 (2019-08)
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
2010.01057 (2020-10)
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
and 6 more not named here
Pooler
brick of this paper's assembly: model
8 other papers
4 dated earlier, 4 later · 7 only as an assembly brick
1908.10084 (2019-08)
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
2104.08821 (2021-04)
SimCSE: Simple Contrastive Learning of Sentence Embeddings
2203.05877 (2022-03)
A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings
and 5 more not named here
cl_forward
brick of this paper's assembly: model
8 other papers
2 dated earlier, 6 later · 2 only as an assembly brick
1908.10084 (2019-08)
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
2104.08821 (2021-04)
SimCSE: Simple Contrastive Learning of Sentence Embeddings
2211.06127 (2022-11)
English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings
and 5 more not named here

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

Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformerbased sentence encoder through a contrastive objective with text, i.e., clustering sentences with semantically similar meanings and scattering others. In this work, we find the performance of Transformer models as sentence encoders can be improved by training with multi-modal multi-task losses, using unpaired examples from another modality (e.g., sentences and unrelated image/audio data). In particular, besides learning by the contrastive loss on text, our model clusters examples from a non-linguistic domain (e.g., visual/audio) with a similar contrastive loss at the same time. The reliance of our framework on unpaired non-linguistic data makes it language-agnostic, enabling it to be widely applicable beyond English NLP. Experiments on 7 semantic textual similarity benchmarks reveal that models trained with the additional non-linguistic (images/audio) contrastive objective lead to higher quality sentence embeddings. This indicates that Transformer models are able to generalize better by doing a similar task (i.e., clustering) with unpaired examples from different modalities in a multi-task fashion. The code is available at https://github.com/yiren-jian/NonLing-CSE. * Contributed as co-first author. 36th Conference on Neural Information Processing Systems (NeurIPS 2022).

For agents

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

get_harvested_code_for_paper("2209.09433")
get_code_for_paper("2209.09433")
have("2209.09433")

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

curl https://syntology.ai/api/ran/2209.09433.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.09433.svg)](https://syntology.ai/paper/2209.09433)

Connect an agent — have() is free.