Papers › Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

5 May 2017EMNLP 2017 9arXiv:1705.02364archive 2025-07-28

Alexis Conneau, Douwe Kiela, Holger Schwenk, Loic Barrault, Antoine Bordes

Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so successful. Several attempts at learning unsupervised representations of sentences have not reached satisfactory enough performance to be widely adopted. In this paper, we show how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks. Much like how computer vision uses ImageNet to obtain features, which can then be transferred to other tasks, our work tends to indicate the suitability of natural language inference for transfer learning to other NLP tasks. Our encoder is publicly available.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 7 code samples harvested from 3 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (1 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 4 samples from 2 repositories, 3 ran (1 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

23 repositories listed; official and paper-mentioned ones first.

facebookresearch/InferSent officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
facebookresearch/SentEval officialmentioned in papermentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
AmanDaVinci/Universal-Sentence-Representations mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SentEval: An Evaluation Toolkit for Universal Sentence Representations (arXiv:1803.05449; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
HareeshBahuleyan/size-fit-net mentioned on GitHubpytorchSyntology: not harvested report
Jessicak016/lstm_nli mentioned on GitHubtfSyntology: not harvested report
MirkoLenz/ReCAP-Argument-Graph-Retrieval mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Universal Sentence Encoder (arXiv:1803.11175; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ReCAP-UTR/Argument-Graph-Retrieval mentioned on GitHubtfApache-2.0Syntology: not harvested report
avinassh/kylo mentioned on GitHubSyntology: not harvested report
boknilev/nmt-repr-analysis mentioned on GitHubpytorchSyntology: not harvested report
cdpierse/transformers-interpret mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Axiomatic Attribution for Deep Networks (arXiv:1703.01365; that paper's own run record: 36 ran (of which 13 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 1 violated, 17 with no contract checked; 15 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
duynguyen158/wann-nlp mentioned on GitHubpytorchSyntology: not harvested report
f-data/ADD mentioned on GitHubtfSyntology: not harvested report
galkesten/Domestic-Violence-Classifier mentioned on GitHubpytorchSyntology: not harvested report
jean-kunz/ml_research_papers mentioned on GitHubtfSyntology: not harvested report
jvdbogae/artverc mentioned on GitHubApache-2.0Syntology: not harvested report
mario-holubar/ATCS-InferSent mentioned on GitHubpytorchSyntology: not harvested report
menajosep/AleatoricSent mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep contextualized word representations (arXiv:1802.05365; that paper's own run record: 30 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 0 violated, 22 with no contract checked; 6 where Syntology's instrument failed) · 28 unverified); nothing checks that they implement this paper's method. report
radoslawkrolikowski/sentiment-analysis-pytorch mentioned on GitHubpytorchSyntology: not harvested report
rajatgermany/qa-nlp mentioned on GitHubpytorchSyntology: not harvested report
rockandroll123/natural-language-inference mentioned on GitHubSyntology: not harvested report
shaanchandra/InferSent mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
sidak/SentEval mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
wbglaeser/brexit-sentiment mentioned on GitHubpytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

7 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
1unverified

Licence: 7 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

facebookresearch/SentEval official repository 3 samples, 3 ran (2 instrument-failed) · 0 unverified
batcher in 15 papers examples/bow.py ran · honoured contract licence not identified · pointer only · ff910817bb9f0411 · report fixture: signature params:Params/0/?, batch:list/1/list · returned ndarray · level recorded 2026-09-22
create_dictionary in 8 papers examples/bow.py ran · our draft was wrong licence not identified · pointer only · af7388308de7ccb4 · report fixture: signature sentences:list/1/list, threshold:int/0/int · returned tuple · level recorded 2026-09-22
get_wordvec in 5 papers examples/bow.py ran · our draft was wrong licence not identified · pointer only · 19d5c2686259a0af · report fixture: signature path_to_vec:str/0/str, word2id:dict/0/? · returned dict · level recorded 2026-09-22
shaanchandra/InferSent community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
create_dictionary in 8 papers code/senteval.py ran · our draft was wrong no licence file found · pointer only · 6ebd3e9ce17919eb · report fixture: signature sentences:list/1/list, threshold:int/0/int · returned tuple · level recorded 2026-09-22
get_wordvec in 5 papers code/senteval.py ran · our draft was wrong no licence file found · pointer only · f830374dfcc9ad29 · report fixture: returned dict · level recorded 2026-09-22
embed_batch code/senteval.py unverified no licence file found · pointer only · e12fbd7bafb84d3d · report
sidak/SentEval community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
batcher in 15 papers examples/infersent.py ran · honoured contract licence not identified · pointer only · e1c6e7d12d71cb6b · report fixture: signature params:MockParams/0/?, batch:list/1/list · returned ndarray · level recorded 2026-09-22

Tasks

Cross-Lingual Natural Language InferenceNatural Language InferenceSemantic Textual SimilaritySentenceTransfer LearningWord Embeddings

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Lingual Natural Language Inference XNLI Zero-Shot English-to-French X-BiLSTM Accuracy 67.7% #2 of 3 Archive leaderboard report
Cross-Lingual Natural Language Inference XNLI Zero-Shot English-to-French X-CBOW Accuracy 60.3% #3 of 3 Archive leaderboard report
Cross-Lingual Natural Language Inference XNLI Zero-Shot English-to-German X-BiLSTM Accuracy 67.7% #3 of 4 Archive leaderboard report
Cross-Lingual Natural Language Inference XNLI Zero-Shot English-to-German X-CBOW Accuracy 61.0% #4 of 4 Archive leaderboard report
Cross-Lingual Natural Language Inference XNLI Zero-Shot English-to-Spanish X-BiLSTM Accuracy 68.7% #3 of 4 Archive leaderboard report
Cross-Lingual Natural Language Inference XNLI Zero-Shot English-to-Spanish X-CBOW Accuracy 60.7% #4 of 4 Archive leaderboard report
Natural Language Inference SNLI 4096D BiLSTM with max-pooling % Test Accuracy 84.5 #78 of 98 Archive leaderboard report
Natural Language Inference SNLI 4096D BiLSTM with max-pooling % Train Accuracy 85.6 #78 of 98 Archive leaderboard report
Natural Language Inference SNLI 4096D BiLSTM with max-pooling Parameters 40m #78 of 98 Archive leaderboard report
Semantic Textual Similarity MRPC InferSent Accuracy 76.2% #37 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC InferSent F1 83.1% #37 of 45 Archive leaderboard report
Semantic Textual Similarity SentEval InferSent MRPC 76.2/83.1 #2 of 6 Archive leaderboard report
Semantic Textual Similarity SentEval InferSent SICK-E 86.3 #2 of 6 Archive leaderboard report
Semantic Textual Similarity SentEval InferSent SICK-R 0.884 #2 of 6 Archive leaderboard report
Semantic Textual Similarity SentEval InferSent STS 75.8/75.5 #2 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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