Papers › TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised...

TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning

14 Apr 2021arXiv:2104.06979archive 2025-07-28

Kexin Wang, Nils Reimers, Iryna Gurevych

Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In this work, we present a new state-of-the-art unsupervised method based on pre-trained Transformers and Sequential Denoising Auto-Encoder (TSDAE) which outperforms previous approaches by up to 6.4 points. It can achieve up to 93.1% of the performance of in-domain supervised approaches. Further, we show that TSDAE is a strong domain adaptation and pre-training method for sentence embeddings, significantly outperforming other approaches like Masked Language Model. A crucial shortcoming of previous studies is the narrow evaluation: Most work mainly evaluates on the single task of Semantic Textual Similarity (STS), which does not require any domain knowledge. It is unclear if these proposed methods generalize to other domains and tasks. We fill this gap and evaluate TSDAE and other recent approaches on four different datasets from heterogeneous domains.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2104.06979")

Code

Syntology Ran 0 of 4 code samples harvested from 1 repository linked to this paper; 4 have no recorded run.

By repository: official repository: 4 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kwang2049/pytorch-bertflow officialmentioned in papermentioned on GitHubpytorch report
kwang2049/useb officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
ukplab/pytorch-bertflow officialmentioned in papermentioned on GitHubpytorch report
UKPLab/useb mentioned on GitHubpytorchApache-2.0 report
climsocana/tecb-de mentioned on GitHub report
exploration-lab/iitk-semeval-2024-task-1 mentioned on GitHubpytorchMIT 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.

Code Syntology ran Syntology

4 samples harvested; 0 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4unverified

Licence: 0 of the 4 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 kwang2049/useb. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

ap_score kwang2049/useb/useb/evaluators/askubuntu.py official repository unverified Apache-2.0 (permissive) · 98ef1f429528f0af · report
rank_by_score kwang2049/useb/useb/evaluators/askubuntu.py official repository unverified Apache-2.0 (permissive) · f8c5243b757f193d · report
reciprocal_rank kwang2049/useb/useb/evaluators/askubuntu.py official repository unverified Apache-2.0 (permissive) · 4ea966908d8fd441 · report
run kwang2049/useb/useb/evaluating.py official repository unverified Apache-2.0 (permissive) · 4b4d63cfd3f3c390 · report

Tasks

DenoisingDomain AdaptationInformation RetrievalLanguage ModelingLanguage ModellingParaphrase IdentificationRe-RankingSTSSemantic Textual SimilaritySentenceSentence EmbeddingSentence EmbeddingsSentence-Embedding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Information Retrieval CQADupStack TSDAE mAP@100 0.145 #2 of 2 Archive leaderboard report
Paraphrase Identification PIT TSDAE AP 69.2 #1 of 1 Archive leaderboard report
Paraphrase Identification TURL TSDAE AP 76.8 #1 of 1 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.

Methods

Introduced by this paper: TSDAE

AttentionSoftmaxTSDAE

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