Rising computational demands of modern natural language processing (NLP)...
Web-scale search systems learn an encoder to embed a given query which i...
Large-scale vision language (VL) models use Transformers to perform
cros...
The Outstanding performance and growing size of Large Language Models ha...
Open domain question answering (ODQA) is a longstanding task aimed at
an...
Getting the most out of limited resources allows advances in natural lan...
Existing software-based energy measurements of NLP models are not accura...
We present BewQA, a system specifically designed to answer a class of
qu...
Accurate and reliable measurement of energy consumption is critical for
...
Transformer-based QA models use input-wide self-attention – i.e. across ...
In this paper, we explore optimizations to run Recurrent Neural Network ...