SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.11239 · ACL · 2022

DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization

Andrew Arnold, Dan Roth, Zheng Li, Bing Xiang, Zijian Wang, Ming Tan, Ramesh Nallapati, Parminder Bhatia

arXiv · PDF · Open in the Atlas

Code that ran

1 of 5 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 4 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/2203.11239.json · badge: /api/ran/2203.11239.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
amazon-science/dq-bart community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
amazon-research/dq-bart marked official in Papers with Code
Papers with Code archive
0 ran · 4 no recorded run
FunctionStatusWhere it lives
shift_tokens_right Ran
ran; our contract draft was wrong, not the code
amazon-science/dq-bart/quant/modeling_bart_quant.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from facebookresearch/ternary_binary_transformer, is pointer only (licence: NOASSERTION) · get_code("cfb09657fff12fcf")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from facebookresearch/ternary_binary_transformer, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

BartAttention Not yet run
unverified (harvested, no recorded run)
amazon-research/dq-bart/quant/modeling_bart_quant.py
code served (permissive licence) · get_code("d6c6618f516d3fd8")
How it ran

no invocation recorded.

QuantizeLinear Not yet run
unverified (harvested, no recorded run)
amazon-research/dq-bart/quant/modeling_bart_quant.py
code served (permissive licence) · get_code("07ed61cb853ea6a3")
How it ran

no invocation recorded.

SymQuantizer Not yet run
unverified (harvested, no recorded run)
amazon-research/dq-bart/quant/modeling_bart_quant.py
code served (permissive licence) · get_code("ffb85404b46a909f")
How it ran

no invocation recorded.

TwnQuantizer Not yet run
unverified (harvested, no recorded run)
amazon-research/dq-bart/quant/modeling_bart_quant.py
code served (permissive licence) · get_code("d911f3b983515d26")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 4 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
shift_tokens_right 18 other papers
1 dated earlier, 1 the same month, 16 later · 1 only as an assembly brick
2021.acl-demo.21 (2021 (year only))
KuiLeiXi: a Chinese Open-Ended Text Adventure Game
2203.07836 (2022-03)
Graph Pre-training for AMR Parsing and Generation
2210.08474 (2022-10)
Sentence Representation Learning with Generative Objective rather than Contrastive Objective
and 15 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

Large-scale pre-trained sequence-to-sequence models like BART and T5 achieve state-ofthe-art performance on many generative NLP tasks. However, such models pose a great challenge in resource-constrained scenarios owing to their large memory requirements and high latency. To alleviate this issue, we propose to jointly distill and quantize the model, where knowledge is transferred from the fullprecision teacher model to the quantized and distilled low-precision student model. Empirical analyses show that, despite the challenging nature of generative tasks, we were able to achieve a 16.5x model footprint compression ratio with little performance drop relative to the full-precision counterparts on multiple summarization and QA datasets. We further pushed the limit of compression ratio to 27.7x and presented the performance-efficiency tradeoff for generative tasks using pre-trained models. To the best of our knowledge, this is the first work aiming to effectively distill and quantize sequence-to-sequence pre-trained models for language generation tasks.

For agents

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

get_harvested_code_for_paper("2203.11239")
get_code_for_paper("2203.11239")
have("2203.11239")

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

curl https://syntology.ai/api/ran/2203.11239.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.11239.svg)](https://syntology.ai/paper/2203.11239)

Connect an agent — have() is free.