Task Arithmetic for Language Expansion in Speech Translation
Recent advances in large language models (LLMs) have gained interest in speech-text multimodal foundation models, achieving strong performance on instruction-based speech translation (ST). However, expanding language pairs from an existing instruction-tuned ST system is costly due to the necessity o...
Gespeichert in:
Hauptverfasser: | , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Recent advances in large language models (LLMs) have gained interest in
speech-text multimodal foundation models, achieving strong performance on
instruction-based speech translation (ST). However, expanding language pairs
from an existing instruction-tuned ST system is costly due to the necessity of
re-training on a combination of new and previous datasets. We propose to expand
new language pairs by merging the model trained on new language pairs and the
existing model, using task arithmetic. We find that the direct application of
task arithmetic for ST causes the merged model to fail to follow instructions;
thus, generating translation in incorrect languages. To eliminate language
confusion, we propose an augmented task arithmetic method that merges an
additional language control model. It is trained to generate the correct target
language token following the instructions. Our experiments demonstrate that our
proposed language control model can achieve language expansion by eliminating
language confusion. In our MuST-C and CoVoST-2 experiments, it shows up to 4.66
and 4.92 BLEU scores improvement, respectively. In addition, we demonstrate the
use of our task arithmetic framework can expand to a language pair where
neither paired ST training data nor a pre-trained ST model is available. We
first synthesize the ST system from machine translation (MT) systems via task
analogy, then merge the synthesized ST system to the existing ST model. |
---|---|
DOI: | 10.48550/arxiv.2409.11274 |