Papers › Graph Based Network with Contextualized Representations of Turns in Dialogue

Graph Based Network with Contextualized Representations of Turns in Dialogue

9 Sep 2021EMNLP 2021 11arXiv:2109.04008archive 2025-07-28

Bongseok Lee, Yong Suk Choi

Dialogue-based relation extraction (RE) aims to extract relation(s) between two arguments that appear in a dialogue. Because dialogues have the characteristics of high personal pronoun occurrences and low information density, and since most relational facts in dialogues are not supported by any single sentence, dialogue-based relation extraction requires a comprehensive understanding of dialogue. In this paper, we propose the TUrn COntext awaRE Graph Convolutional Network (TUCORE-GCN) modeled by paying attention to the way people understand dialogues. In addition, we propose a novel approach which treats the task of emotion recognition in conversations (ERC) as a dialogue-based RE. Experiments on a dialogue-based RE dataset and three ERC datasets demonstrate that our model is very effective in various dialogue-based natural language understanding tasks. In these experiments, TUCORE-GCN outperforms the state-of-the-art models on most of the benchmark datasets. Our code is available at https://github.com/BlackNoodle/TUCORE-GCN.

PaperPDFConference PDFCodeCode 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="2109.04008")

Code

Syntology Ran 10 of 17 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 6 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 17 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

blacknoodle/tucore-gcn officialmentioned in papermentioned on GitHubjaxMIT 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

17 samples harvested; 10 ran; 6 honoured the contract we drafted; 7 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.

6ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it
7unverified

Licence: 0 of the 17 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 blacknoodle/tucore-gcn. “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.

accuracy blacknoodle/tucore-gcn/run_classifier.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 60df39eb36936e8d · report
convert_to_unicode blacknoodle/tucore-gcn/models/BERT/tokenization.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 1923fc05163d207d · report
gelu blacknoodle/tucore-gcn/pre-trained_model/modeling.py official repository ran · honoured contract fingerprinted MIT (permissive) · 40e9fee2e0b7e278 · report
get_cuda blacknoodle/tucore-gcn/models/BERT/TUCOREGCN_BERT.py official repository ran · honoured contract fingerprinted MIT (permissive) · f43f423bf4cb3982 · report
getpredict blacknoodle/tucore-gcn/evaluate.py official repository ran · our draft was wrong MIT (permissive) · 89590c28ea45a292 · report
getresult blacknoodle/tucore-gcn/evaluate.py official repository ran · honoured contract MIT (permissive) · 47d4d6050a2a0f45 · report
set_optimizer_params_grad blacknoodle/tucore-gcn/run_classifier.py official repository ran · violated contract MIT (permissive) · 6eef567fa75a97ac · report
softmax blacknoodle/tucore-gcn/evaluate.py official repository ran · honoured contract fingerprinted MIT (permissive) · cb5cbea0e8219ff5 · report
warmup_constant blacknoodle/tucore-gcn/optimization.py official repository ran · honoured contract fingerprinted MIT (permissive) · e7d542062316094a · report
warmup_linear blacknoodle/tucore-gcn/optimization.py official repository ran · honoured contract fingerprinted MIT (permissive) · c58d57224530d17e · report
calc_test_result blacknoodle/tucore-gcn/run_classifier.py official repository unverified MIT (permissive) · d1d9ea46d0793176 · report
convert_examples_to_features blacknoodle/tucore-gcn/data.py official repository unverified MIT (permissive) · 522ffabbd69e72b3 · report
load_vocab blacknoodle/tucore-gcn/models/BERT/tokenization.py official repository unverified MIT (permissive) · 91bbcb76dbd7d974 · report
printable_text blacknoodle/tucore-gcn/models/BERT/tokenization.py official repository unverified MIT (permissive) · 0e5615f8994003cf · report
tokenize blacknoodle/tucore-gcn/data.py official repository unverified MIT (permissive) · 3bdbef35e308fc67 · report
tokenize2 blacknoodle/tucore-gcn/data.py official repository unverified MIT (permissive) · 194c1558eab8bcbc · report
warmup_cosine blacknoodle/tucore-gcn/optimization.py official repository unverified MIT (permissive) · 35f7cddf90dd05d4 · report

Tasks

Dialog Relation ExtractionEmotion RecognitionEmotion Recognition in ConversationNatural Language UnderstandingRelation ExtractionSentence

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dialog Relation Extraction DialogRE TUCORE-GCN_RoBERTa F1 (v2) 73.1 #4 of 17 Archive leaderboard report
Dialog Relation Extraction DialogRE TUCORE-GCN_RoBERTa F1c (v2) 65.9 #4 of 17 Archive leaderboard report
Dialog Relation Extraction DialogRE TUCORE-GCN_BERT F1 (v2) 65.5 #10 of 17 Archive leaderboard report
Dialog Relation Extraction DialogRE TUCORE-GCN_BERT F1c (v2) 60.2 #10 of 17 Archive leaderboard report
Emotion Recognition in Conversation DailyDialog TUCORE-GCN_RoBERTa Micro-F1 61.91 #3 of 22 Archive leaderboard report
Emotion Recognition in Conversation DailyDialog TUCORE-GCN_BERT Micro-F1 58.34 #14 of 22 Archive leaderboard report
Emotion Recognition in Conversation EmoryNLP TUCORE-GCN_RoBERTa Weighted-F1 39.24 #11 of 28 Archive leaderboard report
Emotion Recognition in Conversation EmoryNLP TUCORE-GCN_BERT Weighted-F1 36.01 #23 of 28 Archive leaderboard report
Emotion Recognition in Conversation MELD TUCORE-GCN_RoBERTa Weighted-F1 65.36 #32 of 68 Archive leaderboard report
Emotion Recognition in Conversation MELD TUCORE-GCN_BERT Weighted-F1 62.47 #46 of 68 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

AWARE

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