Neural Snowball for Few-Shot Relation Learning

By Tianyu Gao, Xu Han, Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun. 2019

85 citations recorded by the source corpus.

Knowledge graphs typically undergo open-ended growth of new relations. This cannot be well handled by relation extraction that focuses on pre-defined relations with sufficient training data. To address new relations with few-shot instances, we propose a novel bootstrapping approach, Neural Snowball, to learn new relations by transferring semantic knowledge about existing relations. More specifically, we use Relational Siamese Networks (RSN) to learn the metric of relational similarities between instances based on existing relations and their labeled data. Afterwards, given a new relation and its few-shot instances, we use RSN to accumulate reliable instances from unlabeled corpora; these instances are used to train a relation classifier, which can further identify new facts of the new relation. The process is conducted iteratively like a snowball. Experiments show that our model can gather high-quality instances for better few-shot relation learning and achieves significant improvement compared to baselines. Codes and datasets are released on https://github.com/thunlp/Neural-Snowball.

Subfields: Artificial Intelligence, Management Science and Operations Research, 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. Zhiyuan Liu
2. Maosong Sun
3. Zixuan Ke
4. Xu Han
5. Yankai Lin
6. Bin Liu
7. Hu Xu
8. Shafiq R. Joty

In Management Science and Operations Research

1. Maosong Sun
2. Zhiyuan Liu
3. Shafiq R. Joty
4. Chengwei Qin
5. Yankai Lin
6. Yi Cai
7. Peng Li
8. Lei Shu

In Information Extraction

1. Chengwei Qin
2. Shafiq R. Joty
3. Peng Li
4. Maosong Sun
5. Wanxiang Che
6. Yankai Lin
7. Ting-Wei Liu
8. Tianyu Gao

In Meta & Continual Learning

1. Zixuan Ke
2. Bin Liu
3. Chengwei Qin
4. Hu Xu
5. Shafiq R. Joty
6. Lei Shu
7. Haowei Lin
8. Yijia Shao

Citations in the corpus

• Continual Training of Language Models for Few-Shot Learning (2022, methodology): “…space of the few-shot task (Triantafillou et al., 2017; Hu et al., 2018), (ii) data-based methods try to augment additional data to the few-shot set (Benaim and Wolf, 2018; Gao et al., 2020), and (iii) algorithm-based solutions try to improve strategies for searching for the best hypothesis.”
• Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation (2022, methodology): “…157 tions: (i) data-based methods use prior knowledge 158 to augment data to the few-shot set (Santoro et al., 159 2016; Benaim and Wolf, 2018; Gao et al., 2020); 160 (ii) model-based methods reduce the hypothesis 161 space using prior knowledge (Rezende et al., 2016; 162 Triantafillou et…”
• LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5 (2021, methodology): “…of the few-shot task (Triantafillou et al., 2017; Hu et al., 2018), ( ii ) data-based methods that try to augment additional data to the few-shot set (Benaim & Wolf, 2018; Gao et al., 2020b), and ( iii ) algorithm-based solutions that aim to improve strategies for searching for the best hypothesis.”
• A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification (2020, background): “Based on this intuition, a series of few-shot RC models (Mishra et al., 2017; Gao et al., 2019a; Soares et al., 2019; Gao et al., 2020) are proposed and can effectively recognize the novel relations with only a few (e.”
• Continual Relation Learning via Episodic Memory Activation and Reconsolidation (2020, background): “, 2019), and data collection (Riloff et al., 1999; Etzioni et al., 2005; Pantel and Pennacchiotti, 2006; Rozenfeld and Feldman, 2008; Nakashole et al., 2011; Zhu et al., 2009; Gao et al., 2020).”
• Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network (2020, background): “…including text classification (Sun et al., 2019; Geng et al., 2019; Yan et al., 2018; Yu et al., 2018), entity relation classification (Lv et al., 2019; Gao et al., 2019; Ye and Ling, 2019), and dialog act prediction (Vlasov et al., 2018 (Fader et al., 2013; Zhang et al., 2015; Liu et al., 2017).”