| 1 |
Classifying relations via long short term memory networks along shortest dependency paths
|
|
|
|
In: http://aclweb.org/anthology/D/D15/D15-1206.pdf (2015)
|
|
Abstract:
Relation classification is an important re-search arena in the field of natural lan-guage processing (NLP). In this paper, we present SDP-LSTM, a novel neural net-work to classify the relation of two enti-ties in a sentence. Our neural architecture leverages the shortest dependency path (SDP) between two entities; multichan-nel recurrent neural networks, with long short term memory (LSTM) units, pick up heterogeneous information along the SDP. Our proposed model has several dis-tinct features: (1) The shortest dependency paths retain most relevant information (to relation classification), while eliminating irrelevant words in the sentence. (2) The multichannel LSTM networks allow ef-fective information integration from het-erogeneous sources over the dependency paths. (3) A customized dropout strategy regularizes the neural network to allevi-ate overfitting. We test our model on the SemEval 2010 relation classification task, and achieve an F1-score of 83.7%, higher than competing methods in the literature. 1
|
|
URL: http://aclweb.org/anthology/D/D15/D15-1206.pdf
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.698.2157
|
|
BASE
|
|
Hide details
|
|
|
|
|
