Relation extraction between the clinical entities based on the shortest dependency path based LSTM

TL;DR

This paper introduces an efficient clinical relation extraction method using shortest dependency paths and LSTM, outperforming existing systems on the i2b2 dataset by focusing on minimal dependency information.

Contribution

The paper presents a novel relation extraction approach leveraging shortest dependency paths with LSTM, reducing reliance on handcrafted features and improving accuracy in clinical texts.

Findings

Outperforms existing relation extraction systems on i2b2 dataset

Uses only shortest dependency path features, reducing complexity

Effective in extracting relations between clinical entities

Abstract

Owing to the exponential rise in the electronic medical records, information extraction in this domain is becoming an important area of research in recent years. Relation extraction between the medical concepts such as medical problem, treatment, and test etc. is also one of the most important tasks in this area. In this paper, we present an efficient relation extraction system based on the shortest dependency path (SDP) generated from the dependency parsed tree of the sentence. Instead of relying on many handcrafted features and the whole sequence of tokens present in a sentence, our system relies only on the SDP between the target entities. For every pair of entities, the system takes only the words in the SDP, their dependency labels, Part-of-Speech information and the types of the entities as the input. We develop a dependency parser for extracting dependency information. We perform our experiments on the benchmark i2b2 dataset for clinical relation extraction challenge 2010. Experimental results show that our system outperforms the existing systems.