Improving Multi-Head Attention with Capsule Networks

Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gu, Shuhao, Feng, Yang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance. In this paper, we employ capsule networks to comb the information from the multiple heads of the attention so that similar information can be clustered and unique information can be reserved. To this end, we adopt two routing mechanisms of Dynamic Routing and EM Routing, to fulfill the clustering and separating. We conducted experiments on Chinese-to-English and English-to-German translation tasks and got consistent improvements over the strong Transformer baseline.
DOI:10.48550/arxiv.1909.00188