Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction

Proceedings of the 28th International Conference on Computational Linguistics, pages 6399–6410 Barcelona, Spain (Online), December 8-13, 2020 6399 Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction Haiyang Yu1,2∗, Ningyu Zhang1,2∗†, Shumin Deng1,2, Hongbin Ye1,2, Wei Zhang3, Huajun Chen1,2 † 1 Zhejiang University 2 AZFT Joint Lab for Knowledge Engine 3 Alibaba Group {yuhaiyang,zhangningyu,231sm,yehb,huajunsir}@zju.edu.cn lantu.zw@alibaba-inc.com Abstract Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings. However, people can grasp new knowledge by learning a few instances. To this end, we take the first step to study the few-shot relational triple extraction, which has not been well understood. Unlike previous single-task few-shot problems, relational triple extraction is more challenging as the entities and relations have implicit correlations. In this paper, We propose a novel multi-prototype embedding network model to jointly extract the composition of relational triples, namely, entity pairs and correspond- ing relations. To be specific, we design a hybrid prototypical learning mechanism that bridges text and knowledge concerning both entities and relations. Thus, implicit correlations between entities and relations are injected. Additionally, we propose a prototype-aware regularization to learn more representative prototypes. Experimental results demonstrate that the proposed method can improve the performance of the few-shot triple extraction. 1 Introduction Relational Triple Extraction is an essential task in Information Extraction for Natural Language Process- ing (NLP) and Knowledge Graph (KG) (Yu et al., 2017; Huang et al., 2020), which is aimed at detecting a pair of entities along with their relation from unstructured text. For instance, there is a sentence “Paris is known as the romantic capital of France.”, and in this example, an ideal relational triple extraction system should extract the relational triple ⟨Paris, Capital of, France⟩, in which Capital of is the relation of Paris and France. Current works in relational triple extraction typically employ traditional supervised learning based on feature engineering (Kambhatla, 2004; Reichartz et al., 2010) and neural networks (Zeng et al., 2014; Bekoulis et al., 2018a). The main problem with supervised learning models is that they can not perform well on unseen entity types or relation categories (e.g., train a model to extract knowledge triples from the economic text, then run this model to work on scientific articles). As a result, supervised relational triple extraction can not extend to the unseen entity or relation types. A trivial solution is to annotate more data for unseen triple types, then retraining the model with newly annotated data (Zhou et al., 2019). However, this method is usually impractical because of the extremely high cost of annotation. Intuitively, humans can learn about a new concept with limited supervision, e.g., one can detect and classify new entities with 3-5 examples (Grishman et al., 2005). This motivates the setting that we aim at for relational triple extraction: Few-Shot Learning (FSL). In few-shot learning, a trained model rapidly learns a new concept from a few examples while keeping great generalization from observed examples (Vinyals et al., 2016; …

Content truncated to 500 words