SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.13654 · 2022

Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metric

arXiv · PDF · Open in the Atlas

Code that ran

2 of 6 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 2 have no contract verdict; 0 failures 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/2209.13654.json · badge: /api/ran/2209.13654.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/doc-mt-metrics canonical (classifier label)
classifier basis not recorded on the link
2 ran · 4 no recorded run
FunctionStatusWhere it lives
add_context Ran
ran on a synthesized input
amazon-science/doc-mt-metrics/bert_score/add_context.py
code served (permissive licence) · get_code("25bb285ada0f5ab2")
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 1, 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 torch

ARGS = {
    'orig_txt': [
        'This is the first sentence.',
        'This is the second sentence.',
        'This is the third sentence.',
        'This is the fourth sentence.'
    ],
    'context': [
        'This is the first sentence.',
        'This is the second sentence.',
        'This is the third sentence.',
        'This is the fourth sentence.'
    ],
    'doc_ids': [
        'doc1',
        'doc1',
        'doc2',
        'doc2'
    ],
    'sep_token': '</s>',
    'ws': 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, 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
get_data Ran
ran on a synthesized input
amazon-science/doc-mt-metrics/bert_score/get_rescale_baseline/get_rescale_baseline.py
code served (permissive licence) · get_code("40f6add30e9986bf")
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 tuple, 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 numpy as np
import tempfile
import os

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
os.makedirs(os.path.join(temp_dir, 'data', 'paracrawl'), exist_ok=True)

# Create test data file
test_file_path = os.path.join(temp_dir, 'data', 'news.2017.en.shuffled.deduped')
with open(test_file_path, 'w') as f:
    # Write lines with varying word counts (some with < 32 words)
    for i in range(100):
        words = ' '.join([f'word{j}' for j in range(i % 20 + 1)])  # Vary word count
        f.write(words + '\n')

# Monkey-patch the open function to use our temp directory
import builtins
original_open = builtins.open

def mock_open(file_path, *args, **kwargs):
    if 'data/' in file_path:
        file_path = file_path.replace('data/', os.path.join(temp_dir, 'data/'))
    return original_open(file_path, *args, **kwargs)

builtins.open = mock_open

# Set random seed for reproducibility
np.random.seed(42)

ARGS = {
    'lang': 'en'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple 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
get_model Not yet run
unverified (harvested, no recorded run)
amazon-science/doc-mt-metrics/bert_score/bert_score/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cyr19/reproducibility, is pointer only (licence: NONE) · get_code("e655efd76f64a7aa")
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 cyr19/reproducibility, and GitHub detected no licence in that repository 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. No invocation recorded.

get_tokenizer Not yet run
unverified (harvested, no recorded run)
amazon-science/doc-mt-metrics/bert_score/bert_score/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cyr19/reproducibility, is pointer only (licence: NONE) · get_code("8d08178958f5f20d")
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 cyr19/reproducibility, and GitHub detected no licence in that repository 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. No invocation recorded.

score Not yet run
unverified (harvested, no recorded run)
amazon-science/doc-mt-metrics/bert_score/bert_score/score.py
code served (permissive licence) · get_code("efd9b25cfcd27f97")
How it ran

no invocation recorded.

sent_encode Not yet run
unverified (harvested, no recorded run)
amazon-science/doc-mt-metrics/bert_score/bert_score/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cyr19/reproducibility, is pointer only (licence: NONE) · get_code("7aa792f0b1258927")
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 cyr19/reproducibility, and GitHub detected no licence in that repository 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. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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
sent_encode 3 other papers
3 dated earlier · 1 only as an assembly brick
1904.09675 (2019-04)
BERTScore: Evaluating Text Generation with BERT
2202.08479 (2022-02)
On the Evaluation Metrics for Paraphrase Generation
2207.05987 (2022-07)
DocPrompting: GENERATING CODE BY RETRIEVING THE DOCS
get_model 2 other papers
2 dated earlier · 1 only as an assembly brick
1904.09675 (2019-04)
BERTScore: Evaluating Text Generation with BERT
2207.05987 (2022-07)
DocPrompting: GENERATING CODE BY RETRIEVING THE DOCS
get_tokenizer 1 other paper
1 dated earlier
1904.09675 (2019-04)
BERTScore: Evaluating Text Generation with BERT

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

We hypothesize that existing sentence-level machine translation (MT) metrics become less effective when the human reference contains ambiguities. To verify this hypothesis, we present a very simple method for extending pretrained metrics to incorporate context at the document level. We apply our method to three popular metrics, BERTScore, Prism, and COMET, and to the reference free metric COMET-QE. We evaluate the extended metrics on the WMT 2021 metrics shared task using the provided MQM annotations. Our results show that the extended metrics outperform their sentence-level counterparts in about 85% of the tested conditions, when excluding results on low-quality human references. Additionally, we show that our document-level extension of COMET-QE dramatically improves its accuracy on discourse phenomena tasks, outperforming a dedicated baseline by up to 6.1%. Our experimental results support our initial hypothesis and show that a simple extension of the metrics permits them to take advantage of context to resolve ambiguities in the reference.

For agents

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

get_harvested_code_for_paper("2209.13654")
get_code_for_paper("2209.13654")
have("2209.13654")

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

curl https://syntology.ai/api/ran/2209.13654.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.13654.svg)](https://syntology.ai/paper/2209.13654)

Connect an agent — have() is free.