CLMay 25, 2022

Fine-grained Contrastive Learning for Relation Extraction

arXiv:2205.12491v2295 citationsh-index: 32
Originality Incremental advance
AI Analysis

This work addresses noise in distant supervision for relation extraction, an incremental improvement for NLP researchers and practitioners.

The paper tackles the problem of noisy silver labels in relation extraction by proposing FineCL, a method that weights more reliable labels during contrastive learning, resulting in consistent and significant performance gains over state-of-the-art methods on several benchmarks.

Recent relation extraction (RE) works have shown encouraging improvements by conducting contrastive learning on silver labels generated by distant supervision before fine-tuning on gold labels. Existing methods typically assume all these silver labels are accurate and treat them equally; however, distant supervision is inevitably noisy -- some silver labels are more reliable than others. In this paper, we propose fine-grained contrastive learning (FineCL) for RE, which leverages fine-grained information about which silver labels are and are not noisy to improve the quality of learned relationship representations for RE. We first assess the quality of silver labels via a simple and automatic approach we call "learning order denoising," where we train a language model to learn these relations and record the order of learned training instances. We show that learning order largely corresponds to label accuracy -- early-learned silver labels have, on average, more accurate labels than later-learned silver labels. Then, during pre-training, we increase the weights of accurate labels within a novel contrastive learning objective. Experiments on several RE benchmarks show that FineCL makes consistent and significant performance gains over state-of-the-art methods.

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