Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving

TL;DR

This paper introduces the TP-Transformer, which enhances the standard Transformer with explicit relational encoding using Tensor-Product Representations, achieving state-of-the-art results on a challenging math problem dataset.

Contribution

It proposes a novel TP-Attention mechanism that explicitly encodes relations, improving the Transformer’s ability to solve complex math word problems.

Findings

Sets new state-of-the-art on Mathematics Dataset

TP-Attention improves relation encoding in Transformers

Provides better interpretability of attention maps

Abstract

We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure. Our Tensor-Product Transformer (TP-Transformer) sets a new state of the art on the recently-introduced Mathematics Dataset containing 56 categories of free-form math word-problems. The essential component of the model is a novel attention mechanism, called TP-Attention, which explicitly encodes the relations between each Transformer cell and the other cells from which values have been retrieved by attention. TP-Attention goes beyond linear combination of retrieved values, strengthening representation-building and resolving ambiguities introduced by multiple layers of standard attention. The TP-Transformer's attention maps give better insights into how it is capable of solving the Mathematics Dataset's challenging problems. Pretrained models and code will be made available after publication.