LABDA at SemEval-2017 Task 10: Relation Classification between keyphrases via Convolutional Neural Network

Abstract

In this paper, we describe our participation at the subtask of extraction of relationships between two identified keyphrases. This task can be very helpful in improving search engines for scientific articles. Our approach is based on the use of a convolutional neural network (CNN) trained on the training dataset. This deep learning model has already achieved successful results for the extraction relationships between named entities. Thus, our hypothesis is that this model can be also applied to extract relations between keyphrases. The official results of the task show that our architecture obtained an F1-score of 0.38% for Keyphrases Relation Classification. This performance is lower than the expected due to the generic preprocessing phase and the basic configuration of the CNN model, more complex architectures are proposed as future work to increase the classification rate.

SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications

“…Overall B C MayoNLP (Liu et al, 2017) 0.64 0.67 0.23 UKP/EELECTION (Eger et al, 2017) Teams Overall MIT (Lee et al, 2017a) 0.64 s2 rel (Ammar et al, 2017) 0.54 NTNU-2 0.5 LaBDA (Suárez-Paniagua et al, 2017) 0.38 TTI COIN rel (Tsujimura et al, 2017) which are called etc in the text between two keyphrases. Interestingly, the RNN based approach of s2 end2end in Scenario 1 performs better than MayoNLP without using partial annotation of Subtask A.…”