R2D2: Relational Text Decoding with Transformers

TL;DR

This paper introduces R2D2, a transformer-based framework that effectively models the interaction between graph structures and associated text, improving data-to-text generation and clinical note creation.

Contribution

It combines graphical and sequential information processing in a transformer model, addressing limitations of previous methods that ignored either structure or text sequence.

Findings

Outperforms state-of-the-art in four data-to-text tasks

Demonstrates effectiveness in clinical note generation

Utilizes pre-trained BERT-like models for improved performance

Abstract

We propose a novel framework for modeling the interaction between graphical structures and the natural language text associated with their nodes and edges. Existing approaches typically fall into two categories. On group ignores the relational structure by converting them into linear sequences and then utilize the highly successful Seq2Seq models. The other side ignores the sequential nature of the text by representing them as fixed-dimensional vectors and apply graph neural networks. Both simplifications lead to information loss. Our proposed method utilizes both the graphical structure as well as the sequential nature of the texts. The input to our model is a set of text segments associated with the nodes and edges of the graph, which are then processed with a transformer encoder-decoder model, equipped with a self-attention mechanism that is aware of the graphical relations between the nodes containing the segments. This also allows us to use BERT-like models that are already trained on large amounts of text. While the proposed model has wide applications, we demonstrate its capabilities on data-to-text generation tasks. Our approach compares favorably against state-of-the-art methods in four tasks without tailoring the model architecture. We also provide an early demonstration in a novel practical application -- generating clinical notes from the medical entities mentioned during clinical visits.