Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study

Xu, Xin; Chen, Xiang; Ningyu, Zhang,; Xie, Xing; Chen, Xi; Chen, Huajun

doi:10.18653/v1/2022.findings-emnlp.29

Cited by 6 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prompt-based models employ encoder-decoder architecture and convert the classification problem to a text generation problem (Han et al, 2022;Xu et al, 2022). That is, the original text sequence X is reformulated by adding a clozestyle phrase called template.…”

Section: Prompt-based Modelsmentioning

confidence: 99%

Rethinking the Role of Entity Type in Relation Classification

Dai,

Karimi,

Wan

2023

Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacifi

View full text Add to dashboard Cite

Relation Classification (RC)-the task of identifying the relation between a pair of target entities-is a fundamental sub-task of information extraction. RC models built on top of entity information are prevalent, with different variants using entity information, especially entity type information, differently. However, RC models are often benchmarked on datasets that human annotators provide near-perfect entity information, and, state-of-the-art results are reported using gold entity type information. We believe there is a need to understand how the effectiveness of RC models is affected by the correctness of entity type information because in practice this information is provided by imperfect entity recognition models. Our results on six datasets across four domains show that although using gold entity type improves the effectiveness of RC models, incorrect entity types may cause large effectiveness drops on some (but not all) datasets. We propose using Pointwise Mutual Information (PMI) to identify datasets on which RC models may be negatively impacted by incorrect entity type information.

show abstract

Section: Prompt-based Modelsmentioning

confidence: 99%