Effective Attention Modeling for Neural Relation Extraction

Abstract

Relation extraction is the task of determining the relation between two entities in a sentence. Distantly-supervised models are popular for this task. However, sentences can be long and two entities can be located far from each other in a sentence. The pieces of evidence supporting the presence of a relation between two entities may not be very direct, since the entities may be connected via some indirect links such as a third entity or via coreference. Relation extraction in such scenarios becomes more challenging as we need to capture the long-distance interactions among the entities and other words in the sentence. Also, the words in a sentence do not contribute equally in identifying the relation between the two entities. To address this issue, we propose a novel and effective attention model which incorporates syntactic information of the sentence and a multi-factor attention mechanism. Experiments on the New York Times corpus show that our proposed model outperforms prior state-of-the-art models.

Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction

“…Traditionally, researchers (Mintz et al 2009;Riedel, Yao, and McCallum 2010;Hoffmann et al 2011;Zeng et al 2014;Shen and Huang 2016;Ren et al 2017;Jat, Khandelwal, and Talukdar 2017;Vashishth et al 2018;Ye and Ling 2019;Guo, Zhang, and Lu 2019;Nayak and Ng 2019) used a pipeline approach for relation tuple extraction where relations were identified using a classification network after all entities were detected. Su et al (2018) used an encoder-decoder model to extract multiple relations present between two given entities.…”

Leveraging a Joint learning Model to Extract Mixture Symptom Mentions from Traditional Chinese Medicine Clinical Notes

“…For instance, Vashishth et al [ 10 ] and Hoffmann et al [ 12 ] employed external components or knowledge-based methods to assist the relation extraction. Considerably more researchers have utilized deep neural networks to achieve superior performance [ 8 , 9 , 11 ]. This has led to research into the modification and optimization of deep neural network-based models.…”

“…Due to the variety of traits, the extraction pipeline structures are just as diverse. Many researchers have chosen the pipeline approach [8][9][10][11][12] to detect entities and then extract relations between them. For instance, Vashishth et al [10] and Hoffmann et al [12] employed external components or knowledge-based methods to assist the relation extraction.…”

Deep Neural Approaches to Relation Triplets Extraction: a Comprehensive Survey

“…This feature vector is passed to a feed-forward layer with softmax to determine the relation. Nayak and Ng (2019) used dependency distance based multi-focused attention model for this task. Dependency distance helps to identify the important words in the sentences and multifactor attention helps to focus on multiple pieces of evidence for a relation.…”