SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.14883 · EMNLP · 2023

Non-autoregressive Streaming Transformer for Simultaneous Translation

Min Zhang, Yang Feng, Chenze Shao, Shaolei Zhang, Zhengrui Ma, Shoutao Guo

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2310.14883.json · badge: /api/ran/2310.14883.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
ictnlp/NAST canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
ctc_decode Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ictnlp/NAST/NAST/models/torch_imputer/imputer.py
pointer only (licence: NONE) · get_code("3c9757a9030277c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ictnlp/NAST 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.

get_alignment_path Ran
ran, honoured the contract we drafted
ictnlp/NAST/NAST/models/torch_imputer/imputer.py
pointer only (licence: NONE) · get_code("e527b150dcb1fcaf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ictnlp/NAST 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.

get_anneal_value Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ictnlp/NAST/NAST/criterions/utilities.py
pointer only (licence: NONE) · get_code("575ebd3590b18e59")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ictnlp/NAST 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.

merge_two_probs Ran
ran; our contract draft was wrong, not the code
ictnlp/NAST/NAST/generators/prefix_beam_search_logits.py
pointer only (licence: NONE) · get_code("da87751db50ed191")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ictnlp/NAST 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.

parse_anneal_argument Ran
ran, honoured the contract we drafted
ictnlp/NAST/NAST/criterions/utilities.py
pointer only (licence: NONE) · get_code("bcfc4f30d3191b80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ictnlp/NAST 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.

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, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 0 later) and 1 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
ctc_decode 1 other paper
1 dated earlier
2002.08926 (2020-02)
Imputer: Sequence Modelling via Imputation and Dynamic Programming
get_alignment_path 1 other paper
1 dated earlier
2002.08926 (2020-02)
Imputer: Sequence Modelling via Imputation and Dynamic Programming
get_anneal_value 1 other paper
1 the same month
2310.07403 (2023-10)
DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation
parse_anneal_argument 1 other paper
1 the same month
2310.07403 (2023-10)
DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation

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

Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality. However, training these models to achieve high quality while maintaining low latency often leads to a tendency for aggressive anticipation. We argue that such issue stems from the autoregressive architecture upon which most existing SiMT models are built. To address those issues, we propose non-autoregressive streaming Transformer (NAST) which comprises a unidirectional encoder and a non-autoregressive decoder with intra-chunk parallelism. We enable NAST to generate the blank token or repetitive tokens to adjust its READ/WRITE strategy flexibly, and train it to maximize the nonmonotonic latent alignment with an alignmentbased latency loss. Experiments on various SiMT benchmarks demonstrate that NAST outperforms previous strong autoregressive SiMT baselines. Source code is publicly available at https://github.com/ictnlp/NAST.

For agents

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

get_harvested_code_for_paper("2310.14883")
get_code_for_paper("2310.14883")
have("2310.14883")

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

curl https://syntology.ai/api/ran/2310.14883.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.14883.svg)](https://syntology.ai/paper/2310.14883)

Connect an agent — have() is free.