SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.04084 · EMNLP · 2021

Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems

Qi Zhang, Yicheng Zou, Zhihua Liu, Xingwu Hu

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 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, 1 violated it and 2 have no contract verdict; 2 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/2109.04084.json · badge: /api/ran/2109.04084.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
rowitzou/cg-nar canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
RowitZou/CG-nAR community
Papers with Code archive
0 ran · 3 no recorded run
FunctionStatusWhere it lives
all_gather_list Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rowitzou/cg-nar/src/distributed.py
pointer only (licence: MIT); the stored copy get_code serves, from gb-kgp/MEDVOC, is pointer only (licence: NONE) · get_code("66575e439195e14f")
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 gb-kgp/MEDVOC, 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.

batch_size_fn Ran
ran on a synthesized input
rowitzou/cg-nar/src/models/data_loader.py
code served (permissive licence) · get_code("abac55cc6cc7a904")
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 int, ndim 0, dtype family int, 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.

import torch

torch.manual_seed(0)

# Analyzing the function:
# - new: indexed at position 6, expects new[6] to be either None or something with len()
# - count: an integer used for comparisons and arithmetic
# - The function uses global variables (sent_num, max_n_dec_tokens, max_n_enc_tokens)
#   but we don't need to initialize them since they're set inside the function

# new should be a sequence/list with at least 7 elements
# new[6] (tgt) should be either None or a sequence (list/tensor) with a length
new = [None, None, None, None, None, None, [1, 2, 3, 4], None]

# count should be an integer
count = 1

ARGS = {
    "new": new,
    "count": count
}
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 int, ndim 0, dtype family int, 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
collapse_copy_scores Ran
ran on a synthesized input
rowitzou/cg-nar/src/models/generator.py
code served (permissive licence) · get_code("0d2e932fa79d8b61")
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 Tensor, ndim 3, dtype family float, shape (2, 3, 12) 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 torch

torch.manual_seed(0)

class Vocab:
    def __init__(self, itos):
        self.itos = itos
    
    def __len__(self):
        return len(self.itos)

class Batch:
    def __init__(self, src_vocabs):
        self.src_vocabs = src_vocabs

# Create small vocabularies
# itos[i] maps index i to a token id (or 0 for padding)
vocab1 = Vocab([0, 5, 7, 9])  # length 4
vocab2 = Vocab([0, 6, 8, 10])  # length 4

batch = Batch([vocab1, vocab2])

# scores shape: (batch_size=2, seq_len=3, vocab_size=4+4+4=12)
# First 4 dims are tgt_vocab, next 8 are expanded copy scores
tgt_vocab_size = 4
expanded_size = tgt_vocab_size + len(vocab1) + len(vocab2)
scores = torch.randn(2, 3, expanded_size)

ARGS = {
    "scores": scores,
    "batch": batch,
    "tgt_vocab": list(range(tgt_vocab_size)),
    "batch_index": None
}
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 Tensor, ndim 3, dtype family float, shape (2, 3, 12) — shape (2, 3, 12) 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
is_master Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rowitzou/cg-nar/src/distributed.py
pointer only (licence: MIT); the stored copy get_code serves, from gb-kgp/MEDVOC, is pointer only (licence: NONE) · get_code("b80220994c939e73")
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 gb-kgp/MEDVOC, 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.

str2bool Ran
ran, violated the contract we drafted
rowitzou/cg-nar/src/preprocess.py
code served (permissive licence) · get_code("f017532fc389cbfe")
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 bool, 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.

import argparse

def str2bool(v):
    if v.lower() in ('yes', 'true', 't', 'y', '1'):
        return True
    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')

# Setup code to construct valid arguments
ARGS = {
    'v': 'true'
}
Setup block drafted by
a language model, Claude Haiku 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 bool, 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
InsertionTransformerDecoder Not yet run
unverified (harvested, no recorded run)
RowitZou/CG-nAR/src/models/insertion_transformer.py
code served (permissive licence) · get_code("98cd13e617f1ddd5")
How it ran

no invocation recorded.

TransformerDecoder Not yet run
unverified (harvested, no recorded run)
RowitZou/CG-nAR/src/models/insertion_transformer.py
code served (permissive licence) · get_code("b7a8902d93f38505")
How it ran

no invocation recorded.

TransformerDecoderLayer Not yet run
unverified (harvested, no recorded run)
RowitZou/CG-nAR/src/models/insertion_transformer.py
code served (permissive licence) · get_code("6386ca8c7af0efc0")
How it ran

no invocation recorded.

apply_ins_words Not yet run
unverified (harvested, no recorded run)
rowitzou/cg-nar/src/models/insertion_transformer.py
code served (permissive licence) · get_code("0807b139fe209f15")
How it ran

no invocation recorded.

new_arange Not yet run
unverified (harvested, no recorded run)
rowitzou/cg-nar/src/models/insertion_transformer.py
code served (permissive licence) · get_code("5e40de0eec5388cd")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 4 later) and 6 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 82 other papers
47 dated earlier, 2 the same month, 32 later, 1 same year, order not determinable
1510.03055 (2015-10)
A Diversity-Promoting Objective Function for Neural Conversation Models
1703.06490 (2017-03)
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
1710.10467 (2017-10)
Generalized End-to-End Loss for Speaker Verification
and 79 more not named here
new_arange 6 other papers
1 dated earlier, 5 later
2002.03079 (2020-02)
Blank Language Models
2208.06073 (2022-08)
Conditional Antibody Design as 3D Equivariant Graph Translation
2302.01649 (2023-02)
Structure-informed Language Models Are Protein Designers
and 3 more not named here
all_gather_list 5 other papers
2 dated earlier, 2 later, 1 same year, order not determinable
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.14135 (2020-04)
BERT Fine-tuning For Arabic Text Summarization
aaai_16089 (2021 (year only))
Automated Lay Language Summarization of Biomedical Scientific Reviews
and 2 more not named here
is_master 5 other papers
2 dated earlier, 2 later, 1 same year, order not determinable
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.14135 (2020-04)
BERT Fine-tuning For Arabic Text Summarization
aaai_16089 (2021 (year only))
Automated Lay Language Summarization of Biomedical Scientific Reviews
and 2 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Human dialogue contains evolving concepts, and speakers naturally associate multiple concepts to compose a response. However, current dialogue models with the seq2seq framework lack the ability to effectively manage concept transitions and can hardly introduce multiple concepts to responses in a sequential decoding manner. To facilitate a controllable and coherent dialogue, in this work, we devise a conceptguided non-autoregressive model (CG-nAR) for open-domain dialogue generation. The proposed model comprises a multi-concept planning module that learns to identify multiple associated concepts from a concept graph and a customized Insertion Transformer that performs concept-guided non-autoregressive generation to complete a response. The experimental results on two public datasets show that CG-nAR can produce diverse and coherent responses, outperforming state-of-the-art baselines in both automatic and human evaluations with substantially faster inference speed.

For agents

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

get_harvested_code_for_paper("2109.04084")
get_code_for_paper("2109.04084")
have("2109.04084")

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

curl https://syntology.ai/api/ran/2109.04084.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.04084.svg)](https://syntology.ai/paper/2109.04084)

Connect an agent — have() is free.