SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.00294 · 2019

When and Why is Document-level Context Useful in Neural Machine Translation?

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 4 have no contract verdict; 0 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/1910.00294.json · badge: /api/ran/1910.00294.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
ducthanhtran/sockeye_document_context canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
int_greater_or_equal Ran
ran on a synthesized input
ducthanhtran/sockeye_document_context/sockeye/arguments.py
code served (permissive licence) · get_code("9b7eb46d92932889")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import argparse
from typing import Callable

def int_greater_or_equal(threshold: int) -> Callable:
    """
    Returns a method that can be used in argument parsing to check that the argument is greater or equal to `threshold`.

    :param threshold: The threshold that we assume the cli argument value is greater or equal to.
    :return: A method that can be used as a type in argparse.
    """

    def check_greater_equal(value_to_check):
        value_to_check = int(value_to_check)
        if value_to_check < threshold:
            raise argparse.ArgumentTypeError('must be greater or equal to %d.' % threshold)
        return value_to_check
    return check_greater_equal


# Test the function with various thresholds
ARGS = {
    "threshold": 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_args Ran
ran on a synthesized input
ducthanhtran/sockeye_document_context/sockeye/arguments.py
code served (permissive licence) · get_code("dbfe68e8c251c012")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Namespace. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import yaml
import argparse

# Create a temporary YAML file with test arguments
temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False)

test_config = {
    'model_name': 'test_model',
    'batch_size': 32,
    'learning_rate': 0.001,
    'epochs': 10,
    'hidden_dim': 128,
    'dropout': 0.1,
    'use_cuda': False,
}

yaml.dump(test_config, temp_file)
temp_file.close()

ARGS = {
    'fname': temp_file.name,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
multiple_values Ran
ran on a synthesized input
ducthanhtran/sockeye_document_context/sockeye/arguments.py
code served (permissive licence) · get_code("31a971573b8bfe7f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import argparse

# The function uses C.ARG_SEPARATOR, so we need to define it
class C:
    ARG_SEPARATOR = ':'

# Define ARGS dict with all parameters of multiple_values
ARGS = {
    'num_values': 3,
    'greater_or_equal': 0.0,
    'data_type': int
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
parallel_subsample Ran
ran on a synthesized input
ducthanhtran/sockeye_document_context/sockeye/checkpoint_decoder.py
code served (permissive licence) · get_code("0dd5254345198861")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import random
from typing import Any, Dict, Optional, List

# Construct valid arguments for parallel_subsample
# The function takes parallel sequences (list of lists) and subsamples them

# Create sample parallel sequences
# These are sequences that should be sampled in parallel (maintaining alignment)
sequence1 = [10, 20, 30, 40, 50]
sequence2 = ['a', 'b', 'c', 'd', 'e']
sequence3 = [1.1, 2.2, 3.3, 4.4, 5.5]

parallel_sequences = [sequence1, sequence2, sequence3]

sample_size = 3
seed = 42

ARGS = {
    'parallel_sequences': parallel_sequences,
    'sample_size': sample_size,
    'seed': seed
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 later) and 0 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
load_args 3 other papers
1 dated earlier, 2 later
1806.09835 (2018-06)
Graph-to-Sequence Learning using Gated Graph Neural Networks
1911.03109 (2019-11)
Domain Robustness in Neural Machine Translation
2205.04022 (2022-05)
CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality
parallel_subsample 3 other papers
1 dated earlier, 2 later
1806.09835 (2018-06)
Graph-to-Sequence Learning using Gated Graph Neural Networks
1911.03109 (2019-11)
Domain Robustness in Neural Machine Translation
2205.04022 (2022-05)
CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality
int_greater_or_equal 1 other paper
1 dated earlier
1806.09835 (2018-06)
Graph-to-Sequence Learning using Gated Graph Neural Networks
multiple_values 1 other paper
1 dated earlier
1806.09835 (2018-06)
Graph-to-Sequence Learning using Gated Graph Neural Networks

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

Document-level context has received lots of attention for compensating neural machine translation (NMT) of isolated sentences. However, recent advances in document-level NMT focus on sophisticated integration of the context, explaining its improvement with only a few selected examples or targeted test sets. We extensively quantify the causes of improvements by a document-level model in general test sets, clarifying the limit of the usefulness of document-level context in NMT. We show that most of the improvements are not interpretable as utilizing the context. We also show that a minimal encoding is sufficient for the context modeling and very long context is not helpful for NMT.

For agents

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

get_harvested_code_for_paper("1910.00294")
get_code_for_paper("1910.00294")
have("1910.00294")

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

curl https://syntology.ai/api/ran/1910.00294.json

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

[![Syntology run record](https://syntology.ai/api/ran/1910.00294.svg)](https://syntology.ai/paper/1910.00294)

Connect an agent — have() is free.