MIT at SemEval-2017 Task 10: Relation Extraction with Convolutional Neural Networks
This work addresses the problem of extracting relations like synonyms and hyponyms from scholarly articles for researchers and information systems, but it is incremental as it builds on existing neural network approaches.
The paper tackled relation extraction from scientific articles using a convolutional neural network, achieving first place in the SemEval-2017 task 10 for relation extraction with a specific ranking result.
Over 50 million scholarly articles have been published: they constitute a unique repository of knowledge. In particular, one may infer from them relations between scientific concepts, such as synonyms and hyponyms. Artificial neural networks have been recently explored for relation extraction. In this work, we continue this line of work and present a system based on a convolutional neural network to extract relations. Our model ranked first in the SemEval-2017 task 10 (ScienceIE) for relation extraction in scientific articles (subtask C).