Multi-view Interaction Learning for Few-Shot Relation Classification

Han, Yi; Qiao, Linbo; Zheng, Jinfeng; Kan, Zhigang; Feng, Linhui; Gao, Yifu; Tang, Yu; Zhai, Qi; Li, Dongsheng; Liao, Xiangke

doi:10.1145/3459637.3482280

Cited by 8 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• IAN [20], an interactive attention network using inter-instance and intrainstance interactive information to classify the relations.…”

Section: Baselinesmentioning

confidence: 99%

“…[10] adopt contrastive learning and task-adaptive training strategy to focus on hard tasks. [20] propose an interactive attention network that uses interinstance and intra-instance interactive information to produce discriminative instance representations. However, the task of achieving unbiased prototypes is still under-explored.…”

Section: Few-shot Relation Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Enhancement-based prototypical networks for few-shot relation classification

Wang

et al. 2023

World Wide Web

View full text Add to dashboard Cite

Few-shot relation classification is to recognize the semantic relation between an entity pair with very few samples. Prototypical network has proven to be a simple yet effective few-shot learning method for relation extraction. However, under the condition of data scarcity, the relation prototypes we achieve are usually biased compared to the real ones computed from all samples within a relation class. To alleviate this issue, we propose hybrid enhancement-based prototypical networks. In particular, our model contains three main enhancement modules: 1) a queryguided prototype enhancement module using rich interactive information between the support instances and the query instance as guidance to obtain more accurate prototype representations; 2) a query enhancement module to diminish the distribution gap between the query set and the support set; 3) a support enhancement module adopting a pseudo-label strategy to expand the scale of available data. On basis of these modules, we further design a novel prototype attention fusion mechanism to fuse information and compute discriminative relation prototypes for classification. In this way, we hope to obtain unbiased representations closer to our expected prototypes by improving the available data scale and data utilization efficiency. Extensive experimental results on the widely-used FewRel dataset demonstrate the superiority of our proposed model.

show abstract

“…• IAN [20], an interactive attention network using inter-instance and intrainstance interactive information to classify the relations.…”

Section: Baselinesmentioning

confidence: 99%

Section: Few-shot Relation Classificationmentioning

confidence: 99%

Hybrid Enhancement-based prototypical networks for few-shot relation classification

Wang

et al. 2023

World Wide Web

View full text Add to dashboard Cite

show abstract

“…Two types of efforts have been devoted to improving few-shot RC. Firstly, some approaches (Ye and Ling, 2019;Gao et al, 2019a;Han et al, 2021;Ren et al, 2020;Ohashi et al, 2021) design specific model architectures such as using attention mechanism to model complex interactions between labeled instances. However, these approaches are still limited when the few labeled instances are atypical and does not reflect the general patterns of the relation.…”

Section: Related Workmentioning

confidence: 99%

Improving Few-Shot Relation Classification by Prototypical Representation Learning with Definition Text

Li¹,

Zhang²,

Nie³

et al. 2022

Findings of the Association for Computational Linguistics: NAACL 2022

Self Cite

View full text Add to dashboard Cite

Few-shot relation classification is difficult because the few instances available may not represent well the relation patterns. Some existing approaches explored extra information such as relation definition, in addition to the instances, to learn a better relation representation. However, the encoding of the extra information has been performed independently from the labeled instances. In this paper, we propose to learn a prototype encoder from relation definition text in a way that is useful for relation instance classification. To this end, we use a joint training approach to train both a prototype encoder from definition and an instance encoder. Extensive experiments on several datasets demonstrate the effectiveness and usefulness of our prototype encoder from definition text, enabling us to outperform state-ofthe-art approaches.

show abstract

“…KEFDA [262], on the other hand, stands out by incorporating general and domain knowledge into the model. The theme of attention mechanisms continues in IAN [261] and HMNet [263], with each focusing on different aspects. IAN [261] computes inter-and intra-instance correlations to guide fusion operations, while HMNet [263] conducts dual scoring from both entity and relation perspectives for effective link prediction.…”

Section: Few-shot Relation Classificationmentioning

confidence: 99%

“…In contrast, P-INT [275] encodes relations via expressive paths for accurate matching. Similar to IAN [261], CIAN [270] leverages attention mechanisms to capture both intraand inter-entity interactions for better entity pair representations. Meanwhile, NP-FKGC [276] merges normalizing flows and neural processes to manage complex relations and estimate uncertainties, aided by an attentive relation pathbased GNN to better capture KG path information.…”

Section: Few-shot Relation Classificationmentioning

confidence: 99%

The danger of dichloromethane in the synthesis and application of imidazole-based dyes

Liu

Chen

et al. 2022

Dyes and Pigments

View full text Add to dashboard Cite

Multi-view Interaction Learning for Few-Shot Relation Classification

Cited by 8 publications

References 37 publications

Hybrid Enhancement-based prototypical networks for few-shot relation classification

Hybrid Enhancement-based prototypical networks for few-shot relation classification

Improving Few-Shot Relation Classification by Prototypical Representation Learning with Definition Text

The danger of dichloromethane in the synthesis and application of imidazole-based dyes

Contact Info

Product

Resources

About