SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.02208 · ACL · 2021

BERTTune: Fine-Tuning Neural Machine Translation with BERTScore

Inigo Unanue, Jacob Parnell, Massimo Piccardi

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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 3 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2106.02208.json · badge: /api/ran/2106.02208.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
ijauregiCMCRC/fairseq-bert-loss canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
aligned_bert_loss Ran
ran on a synthesized input
ijauregiCMCRC/fairseq-bert-loss/fairseq/criterions/aligned_bert_loss.py
pointer only (licence: MIT) · get_code("2c8538aaf671692c")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ijauregiCMCRC/fairseq-bert-loss, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

bert_loss Ran
ran on a synthesized input
ijauregiCMCRC/fairseq-bert-loss/fairseq/criterions/bert_loss.py
pointer only (licence: MIT) · get_code("01b5843cbc283166")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ijauregiCMCRC/fairseq-bert-loss, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

label_smoothed_nll_loss Ran
ran; our contract draft was wrong, not the code
ijauregiCMCRC/fairseq-bert-loss/fairseq/criterions/lsce_with_bert_regularization.py
code served (permissive licence) · get_code("26da4f92ba56e785")
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) and returned tuple, 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
import torch.nn.functional as F

torch.manual_seed(0)

# Create log probabilities tensor
# Shape: (batch_size=2, vocab_size=4)
# lprobs should be log probabilities, so we use log_softmax
logits = torch.randn(2, 4)
lprobs = F.log_softmax(logits, dim=-1)

# Create target tensor with shape (batch_size=2,)
# Values should be valid indices in range [0, vocab_size)
target = torch.tensor([1, 2], dtype=torch.long)

# Epsilon for label smoothing
epsilon = 0.1

# Ignore index (set to None or a valid index)
ignore_index = None

# Reduce flag
reduce = True

ARGS = {
    "lprobs": lprobs,
    "target": target,
    "epsilon": epsilon,
    "ignore_index": ignore_index,
    "reduce": reduce,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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
padding Ran
ran; our contract draft was wrong, not the code
ijauregiCMCRC/fairseq-bert-loss/fairseq/bert_score/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from yuhui-zh15/nlg_metrics, is pointer only (licence: NONE) · get_code("13ef8eeae8570519")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from yuhui-zh15/nlg_metrics, 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. A run is recorded.

sent_encode Ran
ran on a synthesized input
ijauregiCMCRC/fairseq-bert-loss/fairseq/bert_score/utils.py
pointer only (licence: MIT) · get_code("51475f693de1e034")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ijauregiCMCRC/fairseq-bert-loss, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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_model Not yet run
unverified (harvested, no recorded run)
ijauregiCMCRC/fairseq-bert-loss/fairseq/bert_score/utils.py
code served (permissive licence) · get_code("7e819d1873379c18")
How it ran

no invocation recorded.

score Not yet run
unverified (harvested, no recorded run)
ijauregiCMCRC/fairseq-bert-loss/fairseq/bert_score/score.py
pointer only (licence: MIT) · get_code("0a91572da431f7d0")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ijauregiCMCRC/fairseq-bert-loss, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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, 3 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
label_smoothed_nll_loss 6 other papers
2 dated earlier, 4 later
1610.02424 (2016-10)
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
2002.06714 (2020-02)
Multi-layer Representation Fusion for Neural Machine Translation
2205.13401 (2022-05)
Your Transformer May Not be as Powerful as You Expect
and 3 more not named here
padding 6 other papers
4 dated earlier, 2 later · 1 only as an assembly brick
1904.09675 (2019-04)
BERTScore: Evaluating Text Generation with BERT
1908.05739 (2019-08)
Abductive Commonsense Reasoning
1909.02622 (2019-09)
MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance
and 3 more not named here
get_model 2 other papers
1 dated earlier, 1 later
1904.09675 (2019-04)
BERTScore: Evaluating Text Generation with BERT
2202.08479 (2022-02)
On the Evaluation Metrics for Paraphrase Generation

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

Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on the recently-proposed BERTScore evaluation metric. BERTScore is a scoring function based on contextual embeddings that overcomes the typical limitations of n-gram-based metrics (e.g. synonyms, paraphrases), allowing translations that are different from the references, yet close in the contextual embedding space, to be treated as substantially correct. To be able to use BERTScore as a training objective, we propose three approaches for generating soft predictions, allowing the network to remain completely differentiable end-to-end. Experiments carried out over four, diverse language pairs have achieved improvements of up to 0.58 pp (3.28%) in BLEU score and up to 0.76 pp (0.98%) in BERTScore (F BERT ) when finetuning a strong baseline.

For agents

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

get_harvested_code_for_paper("2106.02208")
get_code_for_paper("2106.02208")
have("2106.02208")

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

curl https://syntology.ai/api/ran/2106.02208.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.02208.svg)](https://syntology.ai/paper/2106.02208)

Connect an agent — have() is free.