Papers › TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents

TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents

23 Jan 2019arXiv:1901.08149archive 2025-07-28

Thomas Wolf, Victor Sanh, Julien Chaumond, Clement Delangue

We introduce a new approach to generative data-driven dialogue systems (e.g. chatbots) called TransferTransfo which is a combination of a Transfer learning based training scheme and a high-capacity Transformer model. Fine-tuning is performed by using a multi-task objective which combines several unsupervised prediction tasks. The resulting fine-tuned model shows strong improvements over the current state-of-the-art end-to-end conversational models like memory augmented seq2seq and information-retrieval models. On the privately held PERSONA-CHAT dataset of the Conversational Intelligence Challenge 2, this approach obtains a new state-of-the-art, with respective perplexity, Hits@1 and F1 metrics of 16.28 (45 % absolute improvement), 80.7 (46 % absolute improvement) and 19.5 (20 % absolute improvement).

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 26 code samples harvested from 9 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 26 samples from 9 repositories, 18 ran (11 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

23 repositories listed; official and paper-mentioned ones first.

AjayKhalsa/convai_smile mentioned on GitHubpytorchSyntology: not harvested report
BSlience/end2end-conversational-ai mentioned on GitHubpytorchMITSyntology: not harvested report
CP8315-NNP-JLOPEZ/NNP-Chatbot mentioned on GitHubpytorchMITSyntology: not harvested report
DevHyung/dialogue_cl mentioned on GitHubpytorchSyntology: not harvested report
ErikEkstedt/TurnGPT mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog (arXiv:2010.10874; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
KhueNguyen312/Persona-Chatbot mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Vergangenheit/Conv-AI mentioned on GitHubpytorchMITSyntology: not harvested report
cerebroai/AskIt mentioned on GitHubpytorchMITSyntology: 6 samples, 3 ran (0 instrument-failed) · 3 unverified report
dladustn95/ENMODEL mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (3 instrument-failed) · 0 unverified report
dladustn95/dialogGenerator_transformer mentioned on GitHubpytorchSyntology: not harvested report
dladustn95/enLanguageModel mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
huggingface/transfer-learning-conv-ai mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jsnouffer/transfer-learning-conv-ai mentioned on GitHubpytorchMITSyntology: not harvested report
liliaellouz/wabi-sabi mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
noriyukipy/gptchat mentioned on GitHubpytorchMITSyntology: 6 samples, 3 ran (0 instrument-failed) · 3 unverified report
pranavgollamudi/Chatbot mentioned on GitHubpytorchMITSyntology: not harvested report
samsonleegh/convai_smile mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
the-pythoncoder/councelChatbot2 mentioned on GitHubpytorchMITSyntology: not harvested report
the-pythoncoder/counsel-chat mentioned on GitHubpytorchMITSyntology: not harvested report
thu-coai/CDial-GPT mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
xnancy/convai-transformer mentioned on GitHubpytorchMITSyntology: not harvested report
MindSpore-scientific-2/code-10 mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Normalizing Flows are Capable Generative Models (arXiv:2412.06329; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-13 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SVGDreamer: Text Guided SVG Generation with Diffusion Model (arXiv:2312.16476; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

26 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
4ran · our draft was wrong
3ran; the contract check could not run
10ran
8unverified

Licence: 7 of the 26 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 9 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

KhueNguyen312/Persona-Chatbot community (archive-listed) 1 sample, 0 ran · 1 unverified
top_filtering in 13 papers
census: 5 implementations from 9 papers, 1 distinct output on one shared input
Backend/model/interact.py unverified no licence file found · pointer only · cc247ba2437e3e84 · report
cerebroai/AskIt community (archive-listed) 6 samples, 3 ran (0 instrument-failed) · 3 unverified
generate_response in 23 papers decoder.py ran MIT (permissive) · cbad4369484f0733 · report fixture: signature model:callable/0/?, tokenizer:StandInTokenizer/0/?, context:str/0/str, config:ConfigParser/0/? · returned list · level recorded 2026-09-24
sample_sequence in 8 papers decoder.py ran MIT (permissive) · d769737d0223bb6e · report fixture: signature model:callable/0/?, context:list/1/int, config:ConfigParser/0/? · returned Tensor · level recorded 2026-09-24
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
decoder.py ran fingerprinted MIT (permissive) · 31631ed21a9dd3b3 · report fixture: signature logits:Tensor/2/float, top_k:int/0/int, top_p:float/0/float, filter_value:float/0/float · returned Tensor · level recorded 2026-09-24
download_model_folder model.py unverified MIT (permissive) · 41b82c54e1b15d6d · report
load_model in 479 papers model.py unverified MIT (permissive) · 2f849c7661306814 · report
dladustn95/ENMODEL community (archive-listed) 4 samples, 4 ran (3 instrument-failed) · 0 unverified
average_distributed_scalar in 5 papers bertTran_train.py ran · honoured contract no licence file found · pointer only · ebb24f4dc2a81286 · report fixture: signature scalar:float/0/float, args:Args/0/? · returned float · level recorded 2026-09-22
build_input_from_segments bertTran_train.py ran · our draft was wrong no licence file found · pointer only · 0192b257eca590dd · report fixture: signature source:list/1/int, target:list/1/int, bert_tokenizer:MockBertTokenizer/0/?, tokenizer:MockTokenizer/0/?, lm_labels:bool/0/bool, with_eos:bool/0/bool · returned dict · level recorded 2026-09-22
pad_dataset in 5 papers bertTran_train.py ran · our draft was wrong no licence file found · pointer only · 87d44b2808b48aed · report fixture: signature dataset:dict/0/?, padding:int/0/int · returned dict · level recorded 2026-09-22
top_filtering in 13 papers
census: 5 implementations from 9 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float32
bertTran_interact.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 7996c90fe508c5c8 · report fixture: signature logits:Tensor/1/float, top_k:int/0/int, top_p:float/0/float, threshold:float/0/float, filter_value:float/0/float · returned Tensor · level recorded 2026-09-22
dladustn95/enLanguageModel community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
top_filtering in 13 papers
census: 5 implementations from 9 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float32
interact.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · a07f6a302fe3b9eb · report fixture: signature logits:Tensor/1/float, top_k:int/0/int, top_p:float/0/float, threshold:float/0/float, filter_value:float/0/float · returned Tensor · level recorded 2026-09-22
huggingface/transfer-learning-conv-ai community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
make_logdir utils.py ran fingerprinted MIT (permissive) · 10f1aa81cc87b047 · report fixture: signature model_name:str/0/str · returned str · level recorded 2026-09-25
liliaellouz/wabi-sabi community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
rmv_apostrophe interact.py ran fingerprinted MIT (permissive) · 755e75365f12f49e · report fixture: signature string:str/0/str · returned str · level recorded 2026-09-24
string_transformer tokenize_2.py ran MIT (permissive) · 325cbcf13635d567 · report fixture: signature string:str/0/str, tokenizer:SimpleTokenizer/0/? · returned list · level recorded 2026-09-24
translate in 17 papers integrate_summary.py ran fingerprinted MIT (permissive) · b4f520ecd9ceaa5e · report fixture: signature word:str/0/str · returned str · level recorded 2026-09-24
noriyukipy/gptchat community (archive-listed) 6 samples, 3 ran (0 instrument-failed) · 3 unverified
clean_output in 8 papers gptchat/chatlm/lib.py ran fingerprinted MIT (permissive) · 8a6666cf079c15e4 · report fixture: signature ids:list/1/int, sep_token_id:int/0/int, cls_token_id:int/0/int · returned list · level recorded 2026-09-24
cross_entropy_loss_with_padding gptchat/gpt2.py ran MIT (permissive) · 60687ac481590a5d · report fixture: signature num_labels:int/0/int, pad_token_id:int/0/int · returned function · level recorded 2026-09-24
generate_prepare_inputs_for_generation gptchat/chatlm/lib.py ran MIT (permissive) · e97eae5b76709a23 · report fixture: signature sep_token_id:int/0/int · returned function · level recorded 2026-09-24
init_model in 38 papers gptchat/gpt2.py unverified MIT (permissive) · d0fd73ea11340a75 · report
load_or_init_model gptchat/gpt2.py unverified MIT (permissive) · 88a39d354890aa74 · report
samsonleegh/convai_smile community (archive-listed) 1 sample, 0 ran · 1 unverified
evaluation in 57 papers model_pipeline/model_train.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · e46d6b86df789052 · report
thu-coai/CDial-GPT community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
build_input_from_segments infer.py ran · our draft was wrong MIT (permissive) · 9883f7c396f997ab · report fixture: signature history:list/1/list, reply:list/1/int, tokenizer:MockTokenizer/0/?, with_eos:bool/0/bool · returned tuple · level recorded 2026-09-22
test_data infer.py ran · our draft was wrong MIT (permissive) · 692fe8bc3c032edb · report fixture: signature args:Args/0/? · returned list · level recorded 2026-09-22
top_filtering in 13 papers
census: 5 implementations from 9 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float32
infer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 695eaa24be6f2a1d · report fixture: signature logits:Tensor/1/float, top_k:int/0/int, top_p:float/0/float, threshold:float/0/float, filter_value:float/0/float · returned Tensor · level recorded 2026-09-22

Tasks

Dialogue GenerationInformation RetrievalRetrievalTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dialogue Generation Persona-Chat TransferTransfo Avg F1 19.09 #3 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLSTMLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSeq2SeqSigmoid ActivationSoftmaxTanh ActivationTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections