PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction

TL;DR

This paper introduces PARE, a simple yet effective baseline for distantly supervised relation extraction that concatenates all sentences in a bag and encodes them jointly with BERT, outperforming existing models.

Contribution

The paper proposes a novel baseline approach that encodes all sentences in a bag jointly, improving performance over prior methods in monolingual and multilingual DS-RE.

Findings

PARE outperforms state-of-the-art DS-RE models on multiple datasets.

Joint encoding of sentences enhances relation extraction accuracy.

The approach is effective for both monolingual and multilingual settings.

Abstract

Neural models for distantly supervised relation extraction (DS-RE) encode each sentence in an entity-pair bag separately. These are then aggregated for bag-level relation prediction. Since, at encoding time, these approaches do not allow information to flow from other sentences in the bag, we believe that they do not utilize the available bag data to the fullest. In response, we explore a simple baseline approach (PARE) in which all sentences of a bag are concatenated into a passage of sentences, and encoded jointly using BERT. The contextual embeddings of tokens are aggregated using attention with the candidate relation as query -- this summary of whole passage predicts the candidate relation. We find that our simple baseline solution outperforms existing state-of-the-art DS-RE models in both monolingual and multilingual DS-RE datasets.