Improved Relation Extraction with Feature-Rich Compositional Embedding Models

TL;DR

The paper introduces a Feature-rich Compositional Embedding Model (FCM) that combines hand-crafted features with learned embeddings, improving relation extraction across multiple datasets and outperforming previous models.

Contribution

It presents a novel FCM that effectively integrates features and embeddings, addressing limitations of traditional compositional models for relation extraction.

Findings

Outperforms previous compositional and feature-rich models on ACE 2005.

Achieves state-of-the-art results on SemEval 2010.

Demonstrates robustness and generalization across domains.

Abstract

Compositional embedding models build a representation (or embedding) for a linguistic structure based on its component word embeddings. We propose a Feature-rich Compositional Embedding Model (FCM) for relation extraction that is expressive, generalizes to new domains, and is easy-to-implement. The key idea is to combine both (unlexicalized) hand-crafted features with learned word embeddings. The model is able to directly tackle the difficulties met by traditional compositional embeddings models, such as handling arbitrary types of sentence annotations and utilizing global information for composition. We test the proposed model on two relation extraction tasks, and demonstrate that our model outperforms both previous compositional models and traditional feature rich models on the ACE 2005 relation extraction task, and the SemEval 2010 relation classification task. The combination of our model and a log-linear classifier with hand-crafted features gives state-of-the-art results.