CLJan 22, 2018

Unsupervised Open Relation Extraction

arXiv:1801.07174v149 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of unsupervised relation extraction for natural language processing applications, representing an incremental advance.

The paper tackled the problem of extracting relations between named entities from free text in an unsupervised setting, achieving a 5.8% improvement over state-of-the-art with an F1-score of 0.416 on the NYT-FB dataset.

We explore methods to extract relations between named entities from free text in an unsupervised setting. In addition to standard feature extraction, we develop a novel method to re-weight word embeddings. We alleviate the problem of features sparsity using an individual feature reduction. Our approach exhibits a significant improvement by 5.8% over the state-of-the-art relation clustering scoring a F1-score of 0.416 on the NYT-FB dataset.

Code Implementations1 repo
Foundations

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

Your Notes