Modeling Context With Linear Attention for Scalable Document-Level Translation

TL;DR

This paper explores the use of a linear attention model with sentential gating for scalable document-level translation, achieving faster decoding and improved quality over traditional transformers.

Contribution

It demonstrates that linear attention with gating enhances scalability and translation quality, addressing the quadratic complexity issue in long document translation.

Findings

Significantly faster decoding on long sequences.

Comparable or improved BLEU scores.

Sentential gating improves translation quality.

Abstract

Document-level machine translation leverages inter-sentence dependencies to produce more coherent and consistent translations. However, these models, predominantly based on transformers, are difficult to scale to long documents as their attention layers have quadratic complexity in the sequence length. Recent efforts on efficient attention improve scalability, but their effect on document translation remains unexplored. In this work, we investigate the efficacy of a recent linear attention model by Peng et al. (2021) on document translation and augment it with a sentential gate to promote a recency inductive bias. We evaluate the model on IWSLT 2015 and OpenSubtitles 2018 against the transformer, demonstrating substantially increased decoding speed on long sequences with similar or better BLEU scores. We show that sentential gating further improves translation quality on IWSLT.