Papers › Coreferential Reasoning Learning for Language Representation

Coreferential Reasoning Learning for Language Representation

15 Apr 2020EMNLP 2020 11arXiv:2004.06870archive 2025-07-28

Deming Ye, Yankai Lin, Jiaju Du, Zheng-Hao Liu, Peng Li, Maosong Sun, Zhiyuan Liu

Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However, most existing language representation models cannot explicitly handle coreference, which is essential to the coherent understanding of the whole discourse. To address this issue, we present CorefBERT, a novel language representation model that can capture the coreferential relations in context. The experimental results show that, compared with existing baseline models, CorefBERT can achieve significant improvements consistently on various downstream NLP tasks that require coreferential reasoning, while maintaining comparable performance to previous models on other common NLP tasks. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/CorefBERT.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

thunlp/CorefBERT officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
thunlp/KernelGAT officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fine-grained Fact Verification with Kernel Graph Attention Network (arXiv:1910.09796; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Relation Extraction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Extraction DocRED CorefRoBERTa-large F1 60.25 #31 of 62 Archive leaderboard report
Relation Extraction DocRED CorefRoBERTa-large Ign F1 57.90 #31 of 62 Archive leaderboard report
Relation Extraction DocRED CorefBERT-large F1 58.83 #40 of 62 Archive leaderboard report
Relation Extraction DocRED CorefBERT-large Ign F1 56.40 #40 of 62 Archive leaderboard report
Relation Extraction DocRED CorefBERT-base F1 56.96 #46 of 62 Archive leaderboard report
Relation Extraction DocRED CorefBERT-base Ign F1 54.54 #46 of 62 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

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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