A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification

By Haopeng Ren, Yi Cai, Xiaofeng Chen, Guohua Wang, Qing Li. 2020

44 citations recorded by the source corpus.

Relation Classification (RC) plays an important role in natural language processing (NLP). Current conventional supervised and distantly supervised RC models always make a closed-world assumption which ignores the emergence of novel relations in open environment. To incrementally recognize the novel relations, current two solutions (i.e, re-training and lifelong learning) are designed but suffer from the lack of large-scale labeled data for novel relations. Meanwhile, prototypical network enjoys better performance on both fields of deep supervised learning and few-shot learning. However, it still suffers from the incompatible feature embedding problem when the novel relations come in. Motivated by them, we propose a two-phase prototypical network with prototype attention alignment and triplet loss to dynamically recognize the novel relations with a few support instances meanwhile without catastrophic forgetting. Extensive experiments are conducted to evaluate the effectiveness of our proposed model.

Subfields: Artificial Intelligence, Information Extraction, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hang Su
2. Jun Zhu
3. Liyuan Wang
4. Xingxing Zhang
5. Chengwei Qin
6. Shafiq R. Joty
7. Tianyu Pang
8. Yinpeng Dong

In Information Extraction

1. Jun Zhu
2. Chengwei Qin
3. Shafiq R. Joty

In Meta & Continual Learning

1. Xingxing Zhang
2. Liyuan Wang
3. Hang Su
4. Jun Zhu
5. Chengwei Qin
6. Shafiq R. Joty
7. Bin Liu
8. Zixuan Ke

Citations in the corpus

• A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “The applications of continual learning in NLP are also highly diverse, such as dialogue system [130], [131], [260], [260], [282], [298], [437], text classification [87], [172], [325], [460], sentence generation [246], [298], [499], relation learning [343], [357], [455], [465], neural machine transla”
• Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation (2022, methodology): “Based on the observation that the learning of emerging few-shot tasks may result in distorted feature distributions of new data which are incompatible with previous embedding space (Ren et al., 2020), this work introduces a novel model based”