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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1901.08149")

Code

Syntology Ran 8 of 26 code samples harvested from 8 repositories linked to this paper; 18 have no recorded run. Of those that ran: 1 ran · honoured contract; 4 ran · our draft was wrong; 3 ran · fixture could not drive it.

By repository: community (archive-listed): 25 samples from 8 repositories, 8 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

AjayKhalsa/convai_smile mentioned on GitHubpytorch report
BSlience/end2end-conversational-ai mentioned on GitHubpytorchMIT report
CP8315-NNP-JLOPEZ/NNP-Chatbot mentioned on GitHubpytorchMIT report
DevHyung/dialogue_cl mentioned on GitHubpytorch report
ErikEkstedt/TurnGPT mentioned on GitHubpytorch report
KhueNguyen312/Persona-Chatbot mentioned on GitHubpytorch report
Vergangenheit/Conv-AI mentioned on GitHubpytorchMIT report
cerebroai/AskIt mentioned on GitHubpytorchMIT report
dladustn95/ENMODEL mentioned on GitHubpytorch report
dladustn95/dialogGenerator_transformer mentioned on GitHubpytorch report
dladustn95/enLanguageModel mentioned on GitHubpytorch report
huggingface/transfer-learning-conv-ai mentioned on GitHubpytorchMIT report
jsnouffer/transfer-learning-conv-ai mentioned on GitHubpytorchMIT report
liliaellouz/wabi-sabi mentioned on GitHubpytorchMIT report
noriyukipy/gptchat mentioned on GitHubpytorchMIT report
pranavgollamudi/Chatbot mentioned on GitHubpytorchMIT report
samsonleegh/convai_smile mentioned on GitHubpytorch report
the-pythoncoder/councelChatbot2 mentioned on GitHubpytorchMIT report
the-pythoncoder/counsel-chat mentioned on GitHubpytorchMIT report
thu-coai/CDial-GPT mentioned on GitHubpytorch report
xnancy/convai-transformer mentioned on GitHubpytorchMIT 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.

Code Syntology ran Syntology

26 samples harvested; 8 ran; 1 honoured the contract we drafted; 18 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
4ran · our draft was wrong
3ran · fixture could not drive it
18unverified

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 8 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

average_distributed_scalar dladustn95/ENMODEL/bertTran_train.py community (archive-listed) ran · honoured contract no licence file found · pointer only · ebb24f4dc2a81286 · report
build_input_from_segments dladustn95/ENMODEL/bertTran_train.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 0192b257eca590dd · report
build_input_from_segments thu-coai/CDial-GPT/infer.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 9883f7c396f997ab · report
pad_dataset dladustn95/ENMODEL/bertTran_train.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 87d44b2808b48aed · report
test_data thu-coai/CDial-GPT/infer.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 692fe8bc3c032edb · report
top_filtering dladustn95/enLanguageModel/interact.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · a07f6a302fe3b9eb · report
top_filtering dladustn95/ENMODEL/bertTran_interact.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 7996c90fe508c5c8 · report
top_filtering thu-coai/CDial-GPT/infer.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 695eaa24be6f2a1d · report
clean_output noriyukipy/gptchat/gptchat/chatlm/lib.py community (archive-listed) unverified MIT (permissive) · 8a6666cf079c15e4 · report
cosine_similarity cerebroai/AskIt/run_pipeline.py community (archive-listed) unverified MIT (permissive) · c423433d8bc52711 · report
cross_entropy_loss_with_padding noriyukipy/gptchat/gptchat/gpt2.py community (archive-listed) unverified MIT (permissive) · 60687ac481590a5d · report
download_model_folder cerebroai/AskIt/model.py community (archive-listed) unverified MIT (permissive) · 41b82c54e1b15d6d · report
generate noriyukipy/gptchat/gptchat/chatlm/lib.py community (archive-listed) unverified MIT (permissive) · 1d561f2cbca372e3 · report
generate_prepare_inputs_for_generation noriyukipy/gptchat/gptchat/chatlm/lib.py community (archive-listed) unverified MIT (permissive) · e97eae5b76709a23 · report
generate_response cerebroai/AskIt/decoder.py community (archive-listed) unverified MIT (permissive) · cbad4369484f0733 · report
init_model noriyukipy/gptchat/gptchat/gpt2.py community (archive-listed) unverified MIT (permissive) · d0fd73ea11340a75 · report
load_model cerebroai/AskIt/model.py community (archive-listed) unverified MIT (permissive) · 2f849c7661306814 · report
load_or_init_model noriyukipy/gptchat/gptchat/gpt2.py community (archive-listed) unverified MIT (permissive) · 88a39d354890aa74 · report
make_logdir huggingface/transfer-learning-conv-ai/utils.py community (archive-listed) unverified MIT (permissive) · 10f1aa81cc87b047 · report
rmv_apostrophe liliaellouz/wabi-sabi/interact.py community (archive-listed) unverified MIT (permissive) · 755e75365f12f49e · report
sample_sequence cerebroai/AskIt/decoder.py community (archive-listed) unverified MIT (permissive) · d769737d0223bb6e · report
string_transformer liliaellouz/wabi-sabi/tokenize_2.py community (archive-listed) unverified MIT (permissive) · 325cbcf13635d567 · report
top_filtering KhueNguyen312/Persona-Chatbot/Backend/model/interact.py community (archive-listed) unverified no licence file found · pointer only · cc247ba2437e3e84 · report
top_k_top_p_filtering cerebroai/AskIt/decoder.py community (archive-listed) unverified MIT (permissive) · 31631ed21a9dd3b3 · report
translate liliaellouz/wabi-sabi/integrate_summary.py community (archive-listed) unverified MIT (permissive) · b4f520ecd9ceaa5e · report
evaluation identical code first harvested elsewhere unverified licence of this copy not recorded · e46d6b86df789052 · report

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