Relation Classification via Convolutional Deep Neural Network

TLDR

State‑of‑the‑art relation classification relies on statistical machine learning, and its performance is limited by the quality of features extracted from existing NLP systems, which can propagate errors. The study proposes using a convolutional deep neural network to extract lexical and sentence‑level features for relation classification. The method feeds raw word tokens into a convolutional DNN that learns lexical features from nouns and sentence‑level features, concatenates them into a feature vector, and classifies relations with a softmax layer. Experimental results show that this approach significantly outperforms state‑of‑the‑art methods.

Abstract

The state-of-the-art methods used for relation classification are primarily based on statistical machine learning, and their performance strongly depends on the quality of the extracted features. The extracted features are often derived from the output of pre-existing natural language processing (NLP) systems, which leads to the propagation of the errors in the existing tools and hinders the performance of these systems. In this paper, we exploit a convolutional deep neural network (DNN) to extract lexical and sentence level features. Our method takes all of the word tokens as input without complicated pre-processing. First, the word tokens are transformed to vectors by looking up word embeddings 1 . Then, lexical level features are extracted according to the given nouns. Meanwhile, sentence level features are learned using a convolutional approach. These two level features are concatenated to form the final extracted feature vector. Finally, the features are fed into a softmax classifier to predict the relationship between two marked nouns. The experimental results demonstrate that our approach significantly outperforms the state-of-the-art methods.