GADePo: Graph-Assisted Declarative Pooling Transformers for Document-Level Relation Extraction

TL;DR

This paper introduces GADePo, a novel graph-assisted declarative pooling method for document-level relation extraction that replaces hand-coded pooling with explicit graph-based instructions, improving flexibility and performance.

Contribution

It proposes a joint text-graph Transformer with a declarative pooling specification, enabling customizable and domain-guided information aggregation in relation extraction.

Findings

Consistently outperforms hand-coded pooling methods across datasets

Allows flexible, domain-specific pooling strategies

Demonstrates improved relation extraction accuracy

Abstract

Document-level relation extraction typically relies on text-based encoders and hand-coded pooling heuristics to aggregate information learned by the encoder. In this paper, we leverage the intrinsic graph processing capabilities of the Transformer model and propose replacing hand-coded pooling methods with new tokens in the input, which are designed to aggregate information via explicit graph relations in the computation of attention weights. We introduce a joint text-graph Transformer model and a graph-assisted declarative pooling (GADePo) specification of the input, which provides explicit and high-level instructions for information aggregation. GADePo allows the pooling process to be guided by domain-specific knowledge or desired outcomes but still learned by the Transformer, leading to more flexible and customisable pooling strategies. We evaluate our method across diverse datasets and models and show that our approach yields promising results that are consistently better than those achieved by the hand-coded pooling functions.