SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.13679 · 2021

Task-Oriented Dialogue System as Natural Language Generation

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 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 8 have no contract verdict; 1 failure of our instrument; 3 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/2108.13679.json · badge: /api/ran/2108.13679.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
victorwz/tod_as_nlg canonical (classifier label)
classifier basis: census
9 ran · 3 no recorded run
FunctionStatusWhere it lives
batch_get Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
victorwz/tod_as_nlg/Convlab/convlab/lib/util.py
code served (permissive licence) · get_code("b0d15c39202738bd")
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 ndarray, ndim 1, dtype family float, shape (3,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 operator
from collections import deque
import numpy as np

# Test with a list
test_list = ['a', 'b', 'c', 'd', 'e']
test_idxs_list = [0, 2, 4]

# Test with a numpy array
test_array = np.array([10, 20, 30, 40, 50])
test_idxs_array = np.array([1, 3])

# Test with a deque
test_deque = deque(['x', 'y', 'z'])
test_idxs_deque = [0, 2]

# Use list version as the primary test case
ARGS = {
    'arr': test_list,
    'idxs': test_idxs_list
}
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 ndarray, ndim 1, dtype family float, shape (3,) — shape (3,) as a later run recorded it
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
calc_srs_mean_std Ran
ran on a synthesized input
victorwz/tod_as_nlg/Convlab/convlab/lib/util.py
code served (permissive licence) · get_code("a6f04e62859d3452")
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 pandas as pd
import numpy as np

# Create a list of pandas Series with different values
# The function expects a list of Series objects
sr_list = [
    pd.Series([1.0, 2.0, 3.0, 4.0]),
    pd.Series([2.0, 3.0, 4.0, 5.0]),
    pd.Series([3.0, 4.0, 5.0, 6.0])
]

ARGS = {
    "sr_list": sr_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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
calc_ts_diff Ran
ran on a synthesized input
victorwz/tod_as_nlg/Convlab/convlab/lib/util.py
code served (permissive licence) · get_code("1ca922f73a40acc4")
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 str. 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 datetime import datetime

FILE_TS_FORMAT = '%Y_%m_%d_%H%M%S'

def calc_ts_diff(ts2, ts1):
    """
    Calculate the time from tss ts1 to ts2
    @param {str} ts2 Later ts in the FILE_TS_FORMAT
    @param {str} ts1 Earlier ts in the FILE_TS_FORMAT
    @returns {str} delta_t in %H:%M:%S format
    @example

    ts1 = '2017_10_17_084739'
    ts2 = '2017_10_17_084740'
    ts_diff = util.calc_ts_diff(ts2, ts1)
    # => '0:00:01'
    """
    delta_t = datetime.strptime(ts2, FILE_TS_FORMAT) - datetime.strptime(ts1, FILE_TS_FORMAT)
    return str(delta_t)


ARGS = {
    'ts2': '2017_10_17_084740',
    'ts1': '2017_10_17_084739'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_bleu4 Ran
ran on a synthesized input
victorwz/tod_as_nlg/Convlab/convlab/modules/nlg/multiwoz/evaluate.py
code served (permissive licence) · get_code("ad06152cca2a5124")
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 float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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.

# Setup code for get_bleu4 function

# The function expects:
# - dialog_acts: list of dicts mapping dialog act strings to lists of (slot, value) tuples
# - golden_utts: list of reference utterance strings
# - gen_utts: list of generated utterance strings

ARGS = {
    "dialog_acts": [
        {
            "hotel-inform": [("name", "the grand hotel"), ("area", "north")],
            "restaurant-inform": [("food", "italian"), ("pricerange", "moderate")]
        },
        {
            "attraction-inform": [("type", "museum"), ("area", "centre")],
            "taxi-inform": [("type", "taxi"), ("none", "none")]
        }
    ],
    "golden_utts": [
        "The grand hotel is a nice place in the north area with moderate prices.",
        "The museum in the centre is a popular attraction."
    ],
    "gen_utts": [
        "The grand hotel in the north is wonderful and moderately priced.",
        "There is a museum located in the centre area."
    ]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
nltk — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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
initWeights Ran
ran on a synthesized input
victorwz/tod_as_nlg/Convlab/convlab/modules/nlg/multiwoz/utils.py
code served (permissive licence) · get_code("15a0813008eec6f7")
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 ndarray, ndim 2, dtype family float, shape (5, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 math
import numpy as np

np.random.seed(0)

ARGS = {
    "n": 5,
    "d": 3,
}
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 ndarray, ndim 2, dtype family float, shape (5, 3) — shape (5, 3) as a later run recorded it
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
lab_api Ran
ran on a synthesized input
victorwz/tod_as_nlg/Convlab/convlab/lib/decorator.py
code served (permissive licence) · get_code("b7945ad8c3451d39")
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 torch
import torch.nn as nn

def simple_function():
    """A simple function to be decorated."""
    print('foo')
    return "result"

# The lab_api decorator takes a function as its parameter
ARGS = {
    'fn': simple_function
}
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 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
normalize Ran
ran on a synthesized input
victorwz/tod_as_nlg/Convlab/convlab/lib/math_util.py
code served (permissive licence) · get_code("3673b3e2559edfd3")
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 ndarray, ndim 1, dtype family float, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

# Create a small rank-1 numpy array for testing
v = np.array([3.5, 1.2, 8.9, 2.1, 5.5])

ARGS = {
    'v': v
}
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 ndarray, ndim 1, dtype family float, shape (5,) — shape (5,) as a later run recorded it
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
standardize Ran
ran on a synthesized input
victorwz/tod_as_nlg/Convlab/convlab/lib/math_util.py
code served (permissive licence) · get_code("35031fef0defb9d6")
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 ndarray, ndim 1, dtype family float, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

# Create a small rank-1 numpy array for testing
v = np.array([1.0, 2.0, 3.0, 4.0, 5.0])

ARGS = {
    "v": v
}
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 ndarray, ndim 1, dtype family float, shape (5,) — shape (5,) as a later run recorded it
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
to_one_hot Ran
ran on a synthesized input
victorwz/tod_as_nlg/Convlab/convlab/lib/math_util.py
code served (permissive licence) · get_code("bd93e2a982e7fb52")
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 ndarray, ndim 2, dtype family float, shape (5, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

# The function to_one_hot takes:
# - data: an int list (or array-like) of class indices
# - max_val: the maximum value (number of classes for one-hot encoding)

# Create small example data
data = [0, 1, 2, 1, 0]  # List of 5 integer indices
max_val = 3  # Number of classes (0, 1, 2)

ARGS = {
    "data": data,
    "max_val": max_val
}
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 ndarray, ndim 2, dtype family float, shape (5, 3) — shape (5, 3) as a later run recorded it
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
critical Not yet run
unverified (harvested, no recorded run)
victorwz/tod_as_nlg/Convlab/convlab/lib/logger.py
code served (permissive licence) · get_code("fce709c469940c24")
How it ran

no invocation recorded.

debug Not yet run
unverified (harvested, no recorded run)
victorwz/tod_as_nlg/Convlab/convlab/lib/logger.py
code served (permissive licence) · get_code("fa12706c86824fb1")
How it ran

no invocation recorded.

error Not yet run
unverified (harvested, no recorded run)
victorwz/tod_as_nlg/Convlab/convlab/lib/logger.py
code served (permissive licence) · get_code("638bf85c03a64f0d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 10 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
batch_get 1 other paper
1 dated earlier
1912.12482 (2019-12)
SLM Lab: A Comprehensive Benchmark and Modular Software Framework for Reproducible Deep Reinforcement Learning
calc_ts_diff 1 other paper
1 dated earlier
1912.12482 (2019-12)
SLM Lab: A Comprehensive Benchmark and Modular Software Framework for Reproducible Deep Reinforcement Learning

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 propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models like GPT-2 and simplify complicated delexicalization prepossessing. However, directly applying this method heavily suffers from the dialogue entity inconsistency caused by the removal of delexicalized tokens, as well as the catastrophic forgetting problem of the pre-trained model during fine-tuning, leading to unsatisfactory performance. To alleviate these problems, we design a novel GPT-Adapter-CopyNet network, which incorporates the lightweight adapter and CopyNet modules into GPT-2 to achieve better performance on transfer learning and dialogue entity generation. Experimental results conducted on the DSTC8 Track 1 benchmark and MultiWOZ dataset demonstrate that our proposed approach significantly outperforms baseline models with a remarkable performance on automatic and human evaluations.

For agents

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

get_harvested_code_for_paper("2108.13679")
get_code_for_paper("2108.13679")
have("2108.13679")

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

curl https://syntology.ai/api/ran/2108.13679.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.13679.svg)](https://syntology.ai/paper/2108.13679)

Connect an agent — have() is free.