Explicit Pairwise Word Interaction Modeling Improves Pretrained Transformers for English Semantic Similarity Tasks

Abstract: In English semantic similarity tasks, classic word embedding-based approaches explicitly model pairwise "interactions" between the word representations of a sentence pair. Transformer-based pretrained LLMs disregard this notion, instead modeling pairwise word interactions globally and implicitly through their self-attention mechanism. In this paper, we hypothesize that introducing an explicit, constrained pairwise word interaction mechanism to pretrained LLMs improves their effectiveness on semantic similarity tasks. We validate our hypothesis using BERT on four tasks in semantic textual similarity and answer sentence selection. We demonstrate consistent improvements in quality by adding an explicit pairwise word interaction module to BERT.