SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1901.11504 · 2019

Multi-Task Deep Neural Networks for Natural Language Understanding

arXiv · PDF · Open in the Atlas

Code that ran

9 of 13 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; 1 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 5 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/1901.11504.json · badge: /api/ran/1901.11504.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
xycforgithub/MultiTask-MRC community (classifier label)
classifier basis not recorded on the link
7 ran · 4 no recorded run
ABaldrati/MT-BERT reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
cook_refs Ran
ran; our contract draft was wrong, not the code
xycforgithub/MultiTask-MRC/my_utils/bleu_scorer.py
code served (permissive licence) · get_code("7586e1d32f7325f7")
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 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.

from collections import defaultdict

ARGS = {
    'refs': [
        'the quick brown fox jumps over the lazy dog',
        'a quick brown fox leaps over a lazy dog'
    ],
    'eff': 'shortest',
    'n': 4
}
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 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
cook_test Ran
ran; our contract draft was wrong, not the code
xycforgithub/MultiTask-MRC/my_utils/bleu_scorer.py
code served (permissive licence) · get_code("019ae8bc6f98133f")
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 dict. 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.

from collections import defaultdict

def precook(s, n=4, out=False):
    """Takes a string as input and returns an object that can be given to
    either cook_refs or cook_test. This is optional: cook_refs and cook_test
    can take string arguments as well."""
    words = s.split()
    counts = defaultdict(int)
    for k in range(1, n + 1):
        for i in range(len(words) - k + 1):
            ngram = tuple(words[i:i + k])
            counts[ngram] += 1
    return (len(words), counts)

def cook_test(test, xxx_todo_changeme, eff=None, n=4):
    """Takes a test sentence and returns an object that
    encapsulates everything that BLEU needs to know about it."""
    reflen, refmaxcounts = xxx_todo_changeme
    testlen, counts = precook(test, n, True)
    result = {}
    if eff == 'closest':
        result['reflen'] = min(((abs(l - testlen), l) for l in reflen))[1]
    else:
        result['reflen'] = reflen
    result['testlen'] = testlen
    result['guess'] = [max(0, testlen - k + 1) for k in range(1, n + 1)]
    result['correct'] = [0] * n
    for ngram, count in counts.items():
        result['correct'][len(ngram) - 1] += min(refmaxcounts.get(ngram, 0), count)
    return result

# Construct test string
test_string = "the quick brown fox jumps over the lazy dog"

# Construct reference data (precook output)
ref_text = "the quick brown fox jumps over a lazy dog"
ref_length, ref_counts = precook(ref_text, n=4)

# Build xxx_todo_changeme parameter
# It expects (reflen, refmaxcounts)
# reflen should be iterable of lengths, refmaxcounts should be a defaultdict
xxx_todo_changeme_value = ([ref_length], ref_counts)

ARGS = {
    'test': test_string,
    'xxx_todo_changeme': xxx_todo_changeme_value,
    'eff': None,
    'n': 4
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
linear Ran
ran, honoured the contract we drafted
xycforgithub/MultiTask-MRC/src/common.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from MrHuff/Sumo-Net, is pointer only (licence: NONE) · get_code("691b566282a42d88")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from MrHuff/Sumo-Net, 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.

model_config Ran
ran on a synthesized input
xycforgithub/MultiTask-MRC/config.py
code served (permissive licence) · get_code("08a4c368c95d9755")
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 ArgumentParser. 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
import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'parser': argparse.ArgumentParser()
}
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 ArgumentParser — a ArgumentParser output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ArgumentParser 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
postag_func Ran
ran on a synthesized input
xycforgithub/MultiTask-MRC/prepro.py
code served (permissive licence) · get_code("bf7527cf0e0955a9")
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 int; 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 numpy as np

class Token:
    def __init__(self, text, tag_):
        self.text = text
        self.tag_ = tag_

# Create a small vocab dict mapping tags to indices
vocab = {
    "NOUN": 0,
    "VERB": 1,
    "ADJ": 2,
    "ADV": 3,
    "PREP": 4,
}

# Create token objects with text and tag attributes
toks = [
    Token("cat", "NOUN"),
    Token("runs", "VERB"),
    Token("", "PREP"),  # empty text, should be filtered out
    Token("quickly", "ADV"),
    Token("over", "PREP"),
]

ARGS = {
    "toks": toks,
    "vocab": vocab,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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 int — 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
precook Ran
ran; our contract draft was wrong, not the code
xycforgithub/MultiTask-MRC/my_utils/bleu_scorer.py
code served (permissive licence) · get_code("ec4448373d72d636")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 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.

ARGS = {
    "s": "the quick brown fox jumps over the lazy dog",
    "n": 4,
    "out": False
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 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
retry_with_batchsize_halving Ran
ran; our contract draft was wrong, not the code
ABaldrati/MT-BERT/train_glue.py
pointer only (licence: NONE) · get_code("235ffc8c67133e68")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ABaldrati/MT-BERT 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.

split_n Ran
ran; our contract draft was wrong, not the code
ABaldrati/MT-BERT/train_glue.py
pointer only (licence: NONE) · get_code("b686437952d7aa47")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ABaldrati/MT-BERT 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.

str2bool Ran
ran, violated the contract we drafted
xycforgithub/MultiTask-MRC/config.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from haoran0301/amenunet, is pointer only (licence: NONE) · get_code("248284f69adfeaad")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from haoran0301/amenunet, 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.

activation Not yet run
unverified (harvested, no recorded run)
xycforgithub/MultiTask-MRC/src/common.py
code served (permissive licence) · get_code("ed169d65a4e1896a")
How it ran

no invocation recorded.

data_config Not yet run
unverified (harvested, no recorded run)
xycforgithub/MultiTask-MRC/config.py
code served (permissive licence) · get_code("f80bedbbd1203629")
How it ran

no invocation recorded.

init_wrapper Not yet run
unverified (harvested, no recorded run)
xycforgithub/MultiTask-MRC/src/common.py
code served (permissive licence) · get_code("ca57925dc461ab4a")
How it ran

no invocation recorded.

load_data Not yet run
unverified (harvested, no recorded run)
xycforgithub/MultiTask-MRC/prepro.py
code served (permissive licence) · get_code("4dde989e875a2f0a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 5 later) and 8 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
str2bool 33 other papers
12 dated earlier, 21 later
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1506.03134 (2015-06)
Pointer Networks
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning
and 30 more not named here
precook 22 other papers
6 dated earlier, 16 later
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1611.09268 (2016-11)
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
and 19 more not named here
cook_refs 21 other papers
5 dated earlier, 16 later
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1611.09268 (2016-11)
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
1611.09571 (2016-11)
Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model
and 18 more not named here
cook_test 6 other papers
1 dated earlier, 5 later
1611.09268 (2016-11)
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
2109.08365 (2021-09)
CodeQA: A Question Answering Dataset for Source Code Comprehension
2305.18500 (2023-05)
VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
and 3 more not named here
linear 6 other papers
1 dated earlier, 5 later · 1 only as an assembly brick
1803.06585 (2018-03)
Learning Long Term Dependencies via Fourier Recurrent Units
2001.01565 (2020-01)
Stance Detection Benchmark: How Robust Is Your Stance Detection?
2104.04886 (2021-04)
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach
and 3 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

In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks. MT-DNN not only leverages large amounts of cross-task data, but also benefits from a regularization effect that leads to more general representations in order to adapt to new tasks and domains. MT-DNN extends the model proposed in Liu et al. (2015) by incorporating a pre-trained bidirectional transformer language model, known as BERT (Devlin et al., 2018). MT-DNN obtains new state-of-the-art results on ten NLU tasks, including SNLI, SciTail, and eight out of nine GLUE tasks, pushing the GLUE benchmark to 82.7% (2.2% absolute improvement). We also demonstrate using the SNLI and SciTail datasets that the representations learned by MT-DNN allow domain adaptation with substantially fewer in-domain labels than the pre-trained BERT representations. The code and pre-trained models are publicly available at https://github.com/namisan/mt-dnn.

For agents

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

get_harvested_code_for_paper("1901.11504")
get_code_for_paper("1901.11504")
have("1901.11504")

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

curl https://syntology.ai/api/ran/1901.11504.json

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

[![Syntology run record](https://syntology.ai/api/ran/1901.11504.svg)](https://syntology.ai/paper/1901.11504)

Connect an agent — have() is free.