Papers › Task-Oriented Dialogue System as Natural Language Generation

Task-Oriented Dialogue System as Natural Language Generation

31 Aug 2021arXiv:2108.13679archive 2025-07-28

Weizhi Wang, Zhirui Zhang, Junliang Guo, Yinpei Dai, Boxing Chen, Weihua Luo

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.

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="2108.13679")

Code

Syntology Ran 0 of 12 code samples harvested from 1 repository linked to this paper; 12 have no recorded run.

By repository: official repository: 12 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

victorwz/tod_as_nlg officialmentioned in papermentioned 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

12 samples harvested; 0 ran; 0 honoured the contract we drafted; 12 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.

12unverified

Licence: 0 of the 12 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 victorwz/tod_as_nlg. “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.

batch_get victorwz/tod_as_nlg/Convlab/convlab/lib/util.py official repository unverified MIT (permissive) · b0d15c39202738bd · report
calc_srs_mean_std victorwz/tod_as_nlg/Convlab/convlab/lib/util.py official repository unverified MIT (permissive) · a6f04e62859d3452 · report
calc_ts_diff victorwz/tod_as_nlg/Convlab/convlab/lib/util.py official repository unverified MIT (permissive) · 1ca922f73a40acc4 · report
critical victorwz/tod_as_nlg/Convlab/convlab/lib/logger.py official repository unverified MIT (permissive) · fce709c469940c24 · report
debug victorwz/tod_as_nlg/Convlab/convlab/lib/logger.py official repository unverified MIT (permissive) · fa12706c86824fb1 · report
error victorwz/tod_as_nlg/Convlab/convlab/lib/logger.py official repository unverified MIT (permissive) · 638bf85c03a64f0d · report
get_bleu4 victorwz/tod_as_nlg/Convlab/convlab/modules/nlg/multiwoz/evaluate.py official repository unverified MIT (permissive) · ad06152cca2a5124 · report
initWeights victorwz/tod_as_nlg/Convlab/convlab/modules/nlg/multiwoz/utils.py official repository unverified MIT (permissive) · 15a0813008eec6f7 · report
lab_api victorwz/tod_as_nlg/Convlab/convlab/lib/decorator.py official repository unverified MIT (permissive) · b7945ad8c3451d39 · report
normalize victorwz/tod_as_nlg/Convlab/convlab/lib/math_util.py official repository unverified MIT (permissive) · 3673b3e2559edfd3 · report
standardize victorwz/tod_as_nlg/Convlab/convlab/lib/math_util.py official repository unverified MIT (permissive) · 35031fef0defb9d6 · report
to_one_hot victorwz/tod_as_nlg/Convlab/convlab/lib/math_util.py official repository unverified MIT (permissive) · bd93e2a982e7fb52 · report

Tasks

Text GenerationTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAdapterAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPT-2Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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