SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.11963 · 2020

TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation

arXiv · PDF · Open in the Atlas

Code that ran

15 of 15 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; 2 honoured the contract we drafted, 2 violated it and 2 have no contract verdict; 9 failures of our instrument; 0 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/2003.11963.json · badge: /api/ran/2003.11963.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
ShaojieJiang/tldr canonical (classifier label)
classifier basis: census
15 ran · 0 no recorded run
FunctionStatusWhere it lives
built Ran
ran, violated the contract we drafted
ShaojieJiang/tldr/parlai/core/build_data.py
pointer only (licence: MIT) · get_code("09a95f9415277981")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

default_collate Ran
ran; our contract draft was wrong, not the code
ShaojieJiang/tldr/parlai/core/pytorch_data_teacher.py
pointer only (licence: MIT) · get_code("bf6f8d5ab5c677aa")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

ep_length Ran
ran, honoured the contract we drafted
ShaojieJiang/tldr/parlai/core/pytorch_data_teacher.py
pointer only (licence: MIT) · get_code("53876ab3ee29d277")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

escape Ran
ran; our contract draft was wrong, not the code
ShaojieJiang/tldr/parlai/core/dict.py
pointer only (licence: MIT) · get_code("758e9948df81569f")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

find_ngrams Ran
ran; our contract draft was wrong, not the code
ShaojieJiang/tldr/parlai/core/dict.py
pointer only (licence: MIT) · get_code("761ab53c3cc0c21a")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_agent_module Ran
ran; our contract draft was wrong, not the code
ShaojieJiang/tldr/parlai/core/agents.py
pointer only (licence: MIT) · get_code("d4df10ecd89e3877")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_model_dir Ran
ran on a synthesized input
ShaojieJiang/tldr/parlai/core/build_data.py
pointer only (licence: MIT) · get_code("019aeff4cb65bf1a")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_pairs Ran
ran; our contract draft was wrong, not the code
ShaojieJiang/tldr/parlai/core/gpt2_helper.py
pointer only (licence: MIT) · get_code("c083e60f5001bd38")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

load_opt_file Ran
ran; our contract draft was wrong, not the code
ShaojieJiang/tldr/parlai/core/opt.py
pointer only (licence: MIT) · get_code("7fd1f846c6c309b8")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

modelzoo_path Ran
ran on a synthesized input
ShaojieJiang/tldr/parlai/core/build_data.py
pointer only (licence: MIT) · get_code("32c91478736aa14b")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

name_to_agent_class Ran
ran; our contract draft was wrong, not the code
ShaojieJiang/tldr/parlai/core/agents.py
pointer only (licence: MIT) · get_code("e5dd0271001f206e")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

normalize_answer Ran
ran; our contract draft was wrong, not the code
ShaojieJiang/tldr/parlai/core/metrics.py
pointer only (licence: MIT) · get_code("05b2d71076472acd")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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
ShaojieJiang/tldr/parlai/core/params.py
pointer only (licence: MIT) · get_code("1576efd167dc84a8")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

str2floats Ran
ran, honoured the contract we drafted
ShaojieJiang/tldr/parlai/core/params.py
pointer only (licence: MIT) · get_code("e64c262700ca54dd")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

unescape Ran
ran; our contract draft was wrong, not the code
ShaojieJiang/tldr/parlai/core/dict.py
pointer only (licence: MIT) · get_code("7e5138ac467c5625")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ShaojieJiang/tldr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 14 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 0 the same month, 7 later) and 1 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
get_pairs 258 other papers
8 dated earlier, 249 later, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
built 3 other papers
2 dated earlier, 1 later
1906.01603 (2019-06)
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models
2004.05388 (2020-04)
You Impress Me: Dialogue Generation via Mutual Persona Perception
escape 3 other papers
2 dated earlier, 1 later
1906.01603 (2019-06)
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models
2212.07919 (2022-12)
ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning
find_ngrams 3 other papers
2 dated earlier, 1 later
1906.01603 (2019-06)
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models
2212.07919 (2022-12)
ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning
unescape 3 other papers
2 dated earlier, 1 later
1906.01603 (2019-06)
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models
2212.07919 (2022-12)
ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning
get_agent_module 2 other papers
1 dated earlier, 1 later
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models
2004.05388 (2020-04)
You Impress Me: Dialogue Generation via Mutual Persona Perception
name_to_agent_class 2 other papers
1 dated earlier, 1 later
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models
2004.05388 (2020-04)
You Impress Me: Dialogue Generation via Mutual Persona Perception
str2bool 2 other papers
2 dated earlier
1906.01603 (2019-06)
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models
default_collate 1 other paper
1 dated earlier
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models
ep_length 1 other paper
1 dated earlier
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models
get_model_dir 1 other paper
1 dated earlier
1906.01603 (2019-06)
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
load_opt_file 1 other paper
1 dated earlier
1906.01603 (2019-06)
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
normalize_answer 1 other paper
1 dated earlier
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models
str2floats 1 other paper
1 dated earlier
1909.05863 (2019-09)
Finding Generalizable Evidence by Learning to Convince Q&A Models

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

Natural Language Generation (NLG) models are prone to generating repetitive utterances. In this work, we study the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and transformer architectures. To this end, we consider the chit-chat task, where the problem is more prominent than in other tasks that need encoder-decoder architectures. We first study the influence of model architectures. By using pre-attention and highway connections for RNNs, we manage to achieve lower repetition rates. However, this method does not generalize to other models such as transformers. We hypothesize that the deeper reason is that in the training corpora, there are hard tokens that are more difficult for a generative model to learn than others and, once learning has finished, hard tokens are still under-learned, so that repetitive generations are more likely to happen. Based on this hypothesis, we propose token loss dynamic reweighting (TLDR) that applies differentiable weights to individual token losses. By using higher weights for hard tokens and lower weights for easy tokens, NLG models are able to learn individual tokens at different paces. Experiments on chit-chat benchmark datasets show that TLDR is more effective in repetition reduction for both RNN and transformer architectures than baselines using different weighting functions.

For agents

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

get_harvested_code_for_paper("2003.11963")
get_code_for_paper("2003.11963")
have("2003.11963")

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

curl https://syntology.ai/api/ran/2003.11963.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.11963.svg)](https://syntology.ai/paper/2003.11963)

Connect an agent — have() is free.