TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
TACRED (Zhang et al., 2017) is one of the largest, most widely used crowdsourced datasets in Relation Extraction (RE).But, even with recent advances in unsupervised pretraining and knowledge enhanced neural RE, models still show a high error rate.In this paper, we investigate the questions: Have we reached a performance ceiling or is there still room for improvement?And how do crowd annotations, dataset, and models contribute to this error rate?To answer these questions, we first validate the most challenging 5K examples in the development and test sets using trained annotators.We find that label errors account for 8% absolute F1 test error, and that more than 50% of the examples need to be relabeled.On the relabeled test set the average F1 score of a large baseline model set improves from 62.1 to 70.1.After validation, we analyze misclassifications on the challenging instances, categorize them into linguistically motivated error groups, and verify the resulting error hypotheses on three state-of-the-art RE models.We show that two groups of ambiguous relations are responsible for most of the remaining errors and that models may adopt shallow heuristics on the dataset when entities are not masked.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
SpanBERT: Improving Pre-training by Representing and Predicting Spans
Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., & Levy, O. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00300 · Cited by 1,827
SpanBERT: Improving Pre-training by Representing and Predicting Spans
Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., & Levy, O. (2019) · arXiv · doi:10.48550/arxiv.1907.10529 · Cited by 1,827
ERNIE: Enhanced Language Representation with Informative Entities
Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., & Liu, Q. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1139 · Cited by 1,482
Adversarial Examples for Evaluating Reading Comprehension Systems
Jia, R., & Liang, P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1215 · Cited by 1,410
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
Zhang, Y., Qi, P., & Manning, C. D. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1244 · Cited by 1,048
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
McCoy, R. T., Pavlick, E., & Linzen, T. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1334 · Cited by 944
Matching the Blanks: Distributional Similarity for Relation Learning
Baldini Soares, L., FitzGerald, N., Ling, J., & Kwiatkowski, T. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1279 · Cited by 731
Knowledge Enhanced Contextual Word Representations
Peters, M. E., Neumann, M., Logan, R., Schwartz, R., Joshi, V., Singh, S., & Smith, N. A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1005 · Cited by 661
Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
Zintgraf, L. M., Cohen, T. S., Adel, T., & Welling, M. (2017) · arXiv · doi:10.48550/arxiv.1702.04595 · Cited by 487
Probing Neural Network Comprehension of Natural Language Arguments
Niven, T., & Kao, H.-Y. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1459 · Cited by 395
Cited by
KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
Chen, X., Zhang, N., Xie, X., Deng, S., Yao, Y., Tan, C., Huang, F., Si, L., & Chen, H. (2022) · Proceedings of the ACM Web Conference 2022 · doi:10.1145/3485447.3511998 · Cited by 389
Large language models for generative information extraction: a survey
Xu, D., Chen, W., Peng, W., Zhang, C., Xu, T., Zhao, X., Wu, X., Zheng, Y., Wang, Y., & Chen, E. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40555-y · Cited by 326
REBEL: Relation Extraction By End-to-end Language generation
Huguet Cabot, P.-L., & Navigli, R. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.204 · Cited by 261
Revisiting DocRED - Addressing the False Negative Problem in Relation Extraction
Tan, Q., Xu, L., Bing, L., Ng, H. T., & Aljunied, S. M. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.580 · Cited by 207
“Alt et al. (2020) re-annotated a small amount of challenging samples in the development and test sets of the TA-CRED dataset (Zhang et al., 2017).”
Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED
Huang, Q., Hao, S., Ye, Y., Zhu, S., Feng, Y., & Zhao, D. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.432 · Cited by 28
Metadata
- Authors
- Alt, C., Gabryszak, A., & Hennig, L.
- Venue
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Published
- 2020
- Pages
- 1558-1569
- OpenAlex
- W3023215888
- Cited by
- 132
- References
- 11
- FWCI
- 8.67
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.