Abstract
Dependency analysis can assist neural networks to capture semantic features within a sentence for entity relation extraction (RE). Both hard and soft strategies of encoding dependency tree structure have been developed to balance the beneficial extra information against the unfavorable interference in the task of RE. A wide application of graph convolutional network (GCN) in the field of natural language processing (NLP) has demonstrated its effectiveness in encoding the input sentence with the dependency tree structure, as well as its efficiency in parallel computation. This study proposes a novel GCN-based model using multiple representations to depict the dependency tree from various perspectives, and combines those dependency representations afterward to obtain a better sentence representation for relation classification. This model can maximally draw from the sentence the semantic features relevant to the relationship between entities. Results show that our model achieves state-of-the-art performance in terms of the F <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> score (68.0) on the Text Analysis Conference relation extraction dataset (TACRED). In addition, we verify that the renormalization parameter in the GCN operation should be carefully chosen to help GCN-based models achieve its best performance.
Highlights
As a key task for knowledge extraction, relation extraction (RE) is aimed at identifying semantic relatedness between two entities in natural-language documents [1], [2]
On the Text Analysis Conference relation extraction dataset (TACRED), the performance of our model against baseline models in RE is evaluated by micro-averaged precision, recall (R) and F1 score following [14], while the performance on the SemEval dataset is measured by macro F1 score
DepNN [1]: Liu et al introduce the recursive neural network to hierarchically capture dependency subtrees linked to nodes in the shortest dependency path (SDP) and formulate an augmented dependency path (ADP), and apply a convolutional neural network (CNN) to explore important features in the ADP
Summary
As a key task for knowledge extraction, relation extraction (RE) is aimed at identifying semantic relatedness between two entities in natural-language documents [1], [2]. The outputs of the GCN sublayers are fed into a FFNN-based relation classifier, which balances and combines those outputs obtained with different dependency representations before it makes the final decision of the relation classification Such operations comprehensively and flexibly encode the entire dependency structure and maximally retain the useful dependency information for the relation classification. 1) a flexible strategy is developed to comprehensively gather the semantic and syntactic information through a diversity combination approach; 2) an adjustable renormalization parameter γ is introduced in the GCN operation to improve the RE performance; 3) the proposed MDR-GCN model is widely compared with sequence-based, tree-structured and other GCN-based RE models on the TACRED and the SemEval dataset. We provide mathematical and information theoretical foundations in the appendices
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
