Log In Sign Up

Query-Key Normalization for Transformers

by   Alex Henry, et al.

Low-resource language translation is a challenging but socially valuable NLP task. Building on recent work adapting the Transformer's normalization to this setting, we propose QKNorm, a normalization technique that modifies the attention mechanism to make the softmax function less prone to arbitrary saturation without sacrificing expressivity. Specifically, we apply ℓ_2 normalization along the head dimension of each query and key matrix prior to multiplying them and then scale up by a learnable parameter instead of dividing by the square root of the embedding dimension. We show improvements averaging 0.928 BLEU over state-of-the-art bilingual benchmarks for 5 low-resource translation pairs from the TED Talks corpus and IWSLT'15.


Optimizing Transformer for Low-Resource Neural Machine Translation

Language pairs with limited amounts of parallel data, also known as low-...

Transformers without Tears: Improving the Normalization of Self-Attention

We evaluate three simple, normalization-centric changes to improve Trans...

Text normalization for endangered languages: the case of Ligurian

Text normalization is a crucial technology for low-resource languages wh...

Enriching Biomedical Knowledge for Low-resource Language Through Translation

Biomedical data and benchmarks are highly valuable yet very limited in l...

Boosting Transformers for Job Expression Extraction and Classification in a Low-Resource Setting

In this paper, we explore possible improvements of transformer models in...

Small Batch Sizes Improve Training of Low-Resource Neural MT

We study the role of an essential hyper-parameter that governs the train...