Deep learning (DL) is revolutionizing evidence-based decision-making techniques that can
be applied across various sectors. Specifically, it possesses the ability to utilize two or more …

With the urgent demand for generalized deep models, many pre-trained big models are
proposed, such as bidirectional encoder representations (BERT), vision transformer (ViT) …

We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of
Transformer-based neural language models specialized for dialog, which have up to 137B …

Scaling language models with more data, compute and parameters has driven significant
progress in natural language processing. For example, thanks to scaling, GPT-3 was able to …

Text embeddings are useful features in many applications such as semantic search and
computing text similarity. Previous work typically trains models customized for different use …

We introduce INSTRUCTOR, a new method for computing text embeddings given task
instructions: every text input is embedded together with instructions explaining the use case …

This paper presents SimCSE, a simple contrastive learning framework that greatly advances
state-of-the-art sentence embeddings. We first describe an unsupervised approach, which …

Learning high-quality sentence representations benefits a wide range of natural language
processing tasks. Though BERT-based pre-trained language models achieve high …

Abstract Natural Language Processing (NLP) is a branch of artificial intelligence that
involves the design and implementation of systems and algorithms able to interact through …

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined
object categories. This restricted form of supervision limits their generality and usability since …