Exploring various knowledge in relation extraction

TLDR

Extracting semantic relationships between entities is challenging. The paper investigates incorporating diverse lexical, syntactic, and semantic knowledge into feature‑based relation extraction with SVM. The system uses SVM with feature‑based extraction, integrating lexical, syntactic, and semantic resources such as WordNet and Name List. The study shows that phrase chunking alone yields most syntactic gains, while adding full parsing offers limited benefit; incorporating semantic resources further boosts performance, enabling the system to surpass prior state‑of‑the‑art models by over 20 F‑measure points on the ACE relation types.

Abstract

Extracting semantic relationships between entities is challenging. This paper investigates the incorporation of diverse lexical, syntactic and semantic knowledge in feature-based relation extraction using SVM. Our study illustrates that the base phrase chunking information is very effective for relation extraction and contributes to most of the performance improvement from syntactic aspect while additional information from full parsing gives limited further enhancement. This suggests that most of useful information in full parse trees for relation extraction is shallow and can be captured by chunking. We also demonstrate how semantic information such as WordNet and Name List, can be used in feature-based relation extraction to further improve the performance. Evaluation on the ACE corpus shows that effective incorporation of diverse features enables our system outperform previously best-reported systems on the 24 ACE relation subtypes and significantly outperforms tree kernel-based systems by over 20 in F-measure on the 5 ACE relation types.