CLLGNEApr 24, 2015

Classifying Relations by Ranking with Convolutional Neural Networks

arXiv:1504.06580v2592 citations
Originality Highly original
AI Analysis

This addresses the problem of costly feature engineering in relation classification for NLP, offering a state-of-the-art incremental improvement.

The paper tackled relation classification by proposing a convolutional neural network with a pairwise ranking loss (CR-CNN), achieving an F1 score of 84.1 on the SemEval-2010 Task 8 dataset without handcrafted features.

Relation classification is an important semantic processing task for which state-ofthe-art systems still rely on costly handcrafted features. In this work we tackle the relation classification task using a convolutional neural network that performs classification by ranking (CR-CNN). We propose a new pairwise ranking loss function that makes it easy to reduce the impact of artificial classes. We perform experiments using the the SemEval-2010 Task 8 dataset, which is designed for the task of classifying the relationship between two nominals marked in a sentence. Using CRCNN, we outperform the state-of-the-art for this dataset and achieve a F1 of 84.1 without using any costly handcrafted features. Additionally, our experimental results show that: (1) our approach is more effective than CNN followed by a softmax classifier; (2) omitting the representation of the artificial class Other improves both precision and recall; and (3) using only word embeddings as input features is enough to achieve state-of-the-art results if we consider only the text between the two target nominals.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes