Abstract
Relation classification is an important research area in the field of natural language processing (NLP), which aims to recognize the relationship between two tagged entities in a sentence. The noise caused by irrelevant words and the word distance between the tagged entities may affect the relation classification accuracy. In this paper, we present a novel model multi-head attention long short term memory (LSTM) network with filter mechanism (MALNet) to extract the text features and classify the relation of two entities in a sentence. In particular, we combine LSTM with attention mechanism to obtain the shallow local information and introduce a filter layer based on attention mechanism to strength the available information. Besides, we design a semantic rule for marking the key word between the target words and construct a key word layer to extract its semantic information. We evaluated the performance of our model on SemEval-2010 Task8 dataset and KBP-37 dataset. We achieved an F1-score of 86.3% on SemEval-2010 Task8 dataset and F1-score of 61.4% on KBP-37 dataset, which shows that our method is superior to the previous state-of-the-art methods.
Highlights
Relation classification is an important natural language processing (NLP) task
Zhang et al [27] proposed an RCNN (Recurrent Convolutional Neural Networks) model, which combines the advantages of recursive neural network (RNN) and convolutional neural network (CNN)
We propose a novel neural network model MALNet for relation classification
Summary
Relation classification is an important natural language processing (NLP) task. It is the key step in many natural language applications such as information extraction [1,2], construction of knowledge base [3,4], and question answering [5,6]. Apart from the methods mentioned above, some of other works are based on a combination of CNN and RNN to do relation classification tasks [20] They all use the deep learning method to classify the relation more effectively, reducing the time to construct artificial structural features [21,22] and improving the accuracy. 2. Our model differs from most previous models for relation classification, as they rely on the high-level lexical such as dependency parser, part-of speech (POS) tagger, and named entity recognizers (NER) obtained by NLP tools like WordNet; we designed an interactive sentence level attention filter architecture to leave effective local feature information and designed a semantic rule to extract key word for learning more complicated features.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
