# Neural Composition: Learning to Generate from Multiple Models

arXiv: https://arxiv.org/abs/2007.16013 · HTML: https://mlsanity.com/paper/2007.16013/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2020.

## Built on by (most cited first, 3 of 3)

- [Domain-aware Neural Language Models for Speech Recognition](https://mlsanity.com/paper/2101.03229/) (2021)
- [Personalization for BERT-based Discriminative Speech Recognition Rescoring](https://mlsanity.com/paper/2307.06832/) (2023)
- [Towards Continual Entity Learning in Language Models for Conversational Agents](https://mlsanity.com/paper/2108.00082/) (2021)

## Abstract (arXiv)

Decomposing models into multiple components is critically important in many applications such as language modeling (LM) as it enables adapting individual components separately and biasing of some components to the user's personal preferences. Conventionally, contextual and personalized adaptation for language models, are achieved through class-based factorization, which requires class-annotated data, or through biasing to individual phrases which is limited in scale. In this paper, we propose a system that combines model-defined components, by learning when to activate the generation process from each individual component, and how to combine probability distributions from each component, directly from unlabeled text data.