NLP

Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling

December 06, 2021

Abstract

Multi-head attention has each of the attention heads collect salient information from different parts of an input sequence, making it a powerful mechanism for sequence modeling. Multilingual and multi-domain learning are common scenarios for sequence modeling, where the key challenge is to maximize positive transfer and mitigate negative interference across languages and domains. In this paper, we find that non-selective attention sharing is sub-optimal for achieving good generalization across all languages and domains. We further propose attention sharing strategies to facilitate parameter sharing and specialization in multilingual and multi-domain sequence modeling. Our approach automatically learns shared and specialized attention heads for different languages and domains. Evaluated in various tasks including speech recognition, text-to-text and speech-to-text translation, the proposed attention sharing strategies consistently bring gains to sequence models built upon multi-head attention. For speech-to-text translation, our approach yields an average of $+2.0$ BLEU over $13$ language directions in multilingual setting and $+2.0$ BLEU over $3$ domains in multi-domain setting.

Download the Paper

AUTHORS

Written by

Hongyu Gong

Yun Tang

Juan Miguel Pino

Xian Li

Publisher

NeurIPS

Related Publications

November 16, 2021

NLP

Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN

Rahma Chaabouni, Roberto Dessì, Evgeny Kharitonov

November 16, 2021

November 08, 2021

NLP

CORE MACHINE LEARNING

DOBF: A Deobfuscation Pre-Training Objective for Programming Languages

Baptiste Rozière, Marie-Anne Lachaux, Marc Szafraniec, Guillaume Lample

November 08, 2021

October 26, 2021

NLP

Luna: Linear Unified Nested Attention

Xuezhe Ma, Xiang Kong, Sinong Wang, Chunting Zhou, Jonathan May, Hao Ma, Luke Zettlemoyer

October 26, 2021

October 25, 2021

NLP

Unsupervised Speech Recognition

Alexei Baevski, Wei-Ning Hsu, Alexis Conneau, Michael Auli

October 25, 2021