Incorporating Relation Paths in Neural Relation Extraction

By Wenyuan Zeng, Yankai Lin, Zhiyuan Liu, Maosong Sun. 2016

91 citations recorded by the source corpus.

Distantly supervised relation extraction has been widely used to find novel relational facts from plain text. To predict the relation between a pair of two target entities, existing methods solely rely on those direct sentences containing both entities. In fact, there are also many sentences containing only one of the target entities, which also provide rich useful information but not yet employed by relation extraction. To address this issue, we build inference chains between two target entities via intermediate entities, and propose a path-based neural relation extraction model to encode the relational semantics from both direct sentences and inference chains. Experimental results on real-world datasets show that, our model can make full use of those sentences containing only one target entity, and achieves significant and consistent improvements on relation extraction as compared with strong baselines. The source code of this paper can be obtained from https://github.com/thunlp/PathNRE.

Subfields: Artificial Intelligence, Natural Language Processing

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. Philip S. Yu
4. Xu Han
5. Erik Cambria
6. Shirui Pan
7. Xiang Ren
8. Peng Li

In Natural Language Processing

1. Zhiyuan Liu
2. Maosong Sun
3. Xu Han
4. Erik Cambria
5. Peng Li
6. Xiang Ren
7. Pengfei Yu
8. Philip S. Yu

Citations in the corpus

• Neural Logic Machines (2019, background): “Our work is also related to symbolic relational reasoning, which has a wide application in processing discrete data structures such as knowledge graphs and social graphs (Zhu et al., 2014; Kipf & Welling, 2017; Zeng et al., 2017; Yang et al., 2017).”
• FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (2018, methodology): “We evaluate the model proposed by Lin et al. (2016), which is followed by the recent state-of-the-art methods (Zeng et al., 2017; Ji et al., 2017; Huang and Wang, 2017; Wu et al., 2017; Liu et al., 2017; Feng et al., 2018; Zeng et al., 2018), on the benchmark dataset NYT-10 NYT-10 ( Riedel We…”
• Learning Dual Retrieval Module for Semi-supervised Relation Extraction (2019, background): “While many work have been done on developing supervised relation extraction models [4, 24, 36, 38, 39], they typically require a large amount of human-annotated data (i.”
• Semi-supervised Relation Extraction via Incremental Meta Self-Training (2020, unknown): “Current relation extraction methods (Zeng et al. 2016; Zhang et al. 2017) can discover the semantic relation that holds between two entities under supervised learning.”
• Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks (2019, background): “To further improve the performance, some studies incorporate external information (Zeng et al., 2017; Ji et al., 2017; Han et al., 2018a) and advanced training strategies (Ye et al.”
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, methodology): “Side information such as class ties [112] and relation path [113] is also utilized.”
• Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention (2018, methodology): “We evaluate our models on the New York Times (NYT) dataset developed by Riedel et al. (2010), which is widely used in recent works (Lin et al., 2016; Zeng et al., 2017; Ji et al., 2017; Han et al., 2018; Liu et al., 2017; Wu et al., 2017; Huang and Wang, 2017; Feng et al., 2018; Zeng et al., 2018).”