Publications (7)
Play Duration based User-Entity Affinity Modeling in Spoken Dialog System
Bo Xiao, Nicholas Monath, Shankar Ananthakrishnan +1
Multimedia streaming services over spoken dialog systems have become ubiquitous. User-entity affinity modeling is critical for the system to understand and disambiguate user intent…
A Re-ranker Scheme for Integrating Large Scale NLU models
Chengwei Su, Rahul Gupta, Shankar Ananthakrishnan +1
Large scale Natural Language Understanding (NLU) systems are typically trained on large quantities of data, requiring a fast and scalable training strategy. A typical design for NL…
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon AGI, Aaron Langford, Aayush Shah +783
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…
Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems
Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas +38
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller m…
One-vs-All Models for Asynchronous Training: An Empirical Analysis
Rahul Gupta, Aman Alok, Shankar Ananthakrishnan
Any given classification problem can be modeled using multi-class or One-vs-All (OVA) architecture. An OVA system consists of as many OVA models as the number of classes, providing…
Design Considerations For Hypothesis Rejection Modules In Spoken Language Understanding Systems
Aman Alok, Rahul Gupta, Shankar Ananthakrishnan
Spoken Language Understanding (SLU) systems typically consist of a set of machine learning models that operate in conjunction to produce an SLU hypothesis. The generated hypothesis…
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model
Saleh Soltan, Shankar Ananthakrishnan, Jack FitzGerald +13
In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, ar…