Papers › QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation

QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation

19 Oct 2022arXiv:2210.10861archive 2025-07-28

Zhenrui Yue, Huimin Zeng, Bernhard Kratzwald, Stefan Feuerriegel, Dong Wang

Question answering (QA) has recently shown impressive results for answering questions from customized domains. Yet, a common challenge is to adapt QA models to an unseen target domain. In this paper, we propose a novel self-supervised framework called QADA for QA domain adaptation. QADA introduces a novel data augmentation pipeline used to augment training QA samples. Different from existing methods, we enrich the samples via hidden space augmentation. For questions, we introduce multi-hop synonyms and sample augmented token embeddings with Dirichlet distributions. For contexts, we develop an augmentation method which learns to drop context spans via a custom attentive sampling strategy. Additionally, contrastive learning is integrated in the proposed self-supervised adaptation framework QADA. Unlike existing approaches, we generate pseudo labels and propose to train the model via a novel attention-based contrastive adaptation method. The attention weights are used to build informative features for discrepancy estimation that helps the QA model separate answers and generalize across source and target domains. To the best of our knowledge, our work is the first to leverage hidden space augmentation and attention-based contrastive adaptation for self-supervised domain adaptation in QA. Our evaluation shows that QADA achieves considerable improvements on multiple target datasets over state-of-the-art baselines in QA domain adaptation.

PaperPDFCodeCode Syntology ranMethod as code

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 16 code samples: 11 from 1 repository linked to this paper, 5 identical to code harvested from another paper's repository. Across all 16: 12 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 5 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 7 ran (5 with no instrument failure; 2 where Syntology's instrument failed); 5 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

yueeeeeeee/self-supervised-qa officialmentioned in papermentioned on GitHubpytorchSyntology: 11 samples, 7 ran (2 instrument-failed) · 4 unverified 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

16 samples harvested: 12 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 5 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 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.

5ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
2ran
4unverified

Licence: 16 of the 16 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 yueeeeeeee/self-supervised-qa. 5 samples are listed last, in a group without a repository. “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.

yueeeeeeee/self-supervised-qa official repository 11 samples, 7 ran (2 instrument-failed) · 4 unverified
BERTRandomSampler src/run_qada.py ran no licence file found · pointer only · 39391d9b3635435c · report fixture: returned BERTRandomSampler · level recorded 2026-09-22
BertAdam src/run_qada.py ran no licence file found · pointer only · 6fb95e09ee551a2f · report fixture: returned BertAdam · level recorded 2026-09-22
compare_performance src/run_qada.py ran · honoured contract no licence file found · pointer only · cd812ef970436cb7 · report fixture: signature args:ArgsConfig/0/?, best_acc:float/0/float, best_f1:float/0/float, acc:float/0/float, f1:float/0/float, model:callable/0/?, logger:Logger/0/? · returned tuple · level recorded 2026-09-22
evaluate_acc_and_f1 src/run_qada.py ran · honoured contract no licence file found · pointer only · 6e78b0bb4297c189 · report fixture: signature predictions:dict/0/?, raw_data:list/1/Sample, logger:Logger/0/?, threshold:float/0/float, all_probs:dict/0/? · returned tuple · level recorded 2026-09-22
get_bert_model_parameters src/run_qada.py ran · our draft was wrong no licence file found · pointer only · e5f44823bc5e7f55 · report fixture: signature model:callable/0/? · returned list · level recorded 2026-09-22
keep_high_prob_samples src/run_qada.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 71946db113d7b29a · report fixture: signature all_probs:ndarray/1/float, all_features:list/1/Feature, prob_threshold:float/0/float, removed_feature_index:set/0/?, all_indices:list/1/list, keep_generated:bool/0/bool · returned tuple · level recorded 2026-09-22
warmup_constant in 30 papers src/run_qada.py ran · honoured contract fingerprinted no licence file found · pointer only · e7d542062316094a · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-22
comb_adversarial_training_stage src/run_qada.py unverified no licence file found · pointer only · e57c4b1183dcd6cb · report
evaluation_stage src/run_qada.py unverified no licence file found · pointer only · b0b6c98806c9fd6d · report
generate_self_training_samples src/run_qada.py unverified no licence file found · pointer only · 4bdc939ce31c7cf4 · report
warmup_cosine in 30 papers src/run_qada.py unverified no licence file found · pointer only · 35f7cddf90dd05d4 · report
Repository not located 5 samples, 5 ran (2 instrument-failed) · 0 unverified
5 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
exact_match_score in 82 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · f6c275d6a18330a9 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned bool · level recorded 2026-09-22
f1_score in 121 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · 2112c433b9c6d343 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned float · level recorded 2026-09-22
metric_max_over_ground_truths in 12 papers repository not located ran · our draft was wrong licence of this copy not recorded · 6829ceb72569fa12 · report fixture: signature metric_fn:callable/0/?, prediction:Tensor/1/float, ground_truths:list/1/Tensor · returned float · level recorded 2026-09-22
normalize_answer in 304 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · c6a80c065d2e4851 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
warmup_linear in 45 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · c58d57224530d17e · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for QADA (graph method: QADA). 16 bricks; individually on a fixture: 12 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 5 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. comb_adversarial_training_stage entry · level 0 · unverified · e57c4b1183dcd6cb
  2. BERTRandomSampler helper · level 1 · ran · 39391d9b3635435c
  3. BertAdam helper · level 1 · ran · 6fb95e09ee551a2f
  4. compare_performance helper · level 1 · ran · honoured contract · cd812ef970436cb7
  5. evaluation_stage metric · level 0 · unverified · b0b6c98806c9fd6d
  6. generate_self_training_samples data_transform · level 0 · unverified · 4bdc939ce31c7cf4
  7. get_bert_model_parameters helper · level 1 · ran · our draft was wrong · e5f44823bc5e7f55
  8. warmup_linear helper · level 1 · ran · honoured contract · c58d57224530d17e
  9. evaluate_acc_and_f1 helper · level 1 · ran · honoured contract · 6e78b0bb4297c189
  10. keep_high_prob_samples helper · level 1 · ran; the contract check could not run (RAISES) · 71946db113d7b29a
  11. exact_match_score helper · level 1 · ran · violated contract · f6c275d6a18330a9
  12. f1_score helper · level 1 · ran · honoured contract · 2112c433b9c6d343
  13. metric_max_over_ground_truths helper · level 1 · ran · our draft was wrong · 6829ceb72569fa12
  14. normalize_answer helper · level 1 · ran · our draft was wrong · c6a80c065d2e4851
  15. warmup_constant helper · level 1 · ran · honoured contract · e7d542062316094a
  16. warmup_cosine helper · level 0 · unverified · 35f7cddf90dd05d4

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2210.10861") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningData AugmentationDomain AdaptationQuestion Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive Learning

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