Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?
Previous works mostly focus on either multilingual or multi-domain aspects of neural machine translation (NMT). This paper investigates whether the domain information can be transferred across languages on the composition of multi-domain and multilingual NMT, particularly for the incomplete data con...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Previous works mostly focus on either multilingual or multi-domain aspects of
neural machine translation (NMT). This paper investigates whether the domain
information can be transferred across languages on the composition of
multi-domain and multilingual NMT, particularly for the incomplete data
condition where in-domain bitext is missing for some language pairs. Our
results in the curated leave-one-domain-out experiments show that multi-domain
multilingual (MDML) NMT can boost zero-shot translation performance up to +10
gains on BLEU, as well as aid the generalisation of multi-domain NMT to the
missing domain. We also explore strategies for effective integration of
multilingual and multi-domain NMT, including language and domain tag
combination and auxiliary task training. We find that learning domain-aware
representations and adding target-language tags to the encoder leads to
effective MDML-NMT. |
---|---|
DOI: | 10.48550/arxiv.2210.11628 |