Pith. sign in

Regularization techniques for fine-tuning in neural machine translation

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We investigate techniques for supervised domain adaptation for neural machine translation where an existing model trained on a large out-of-domain dataset is adapted to a small in-domain dataset. In this scenario, overfitting is a major challenge. We investigate a number of techniques to reduce overfitting and improve transfer learning, including regularization techniques such as dropout and L2-regularization towards an out-of-domain prior. In addition, we introduce tuneout, a novel regularization technique inspired by dropout. We apply these techniques, alone and in combination, to neural machine translation, obtaining improvements on IWSLT datasets for English->German and English->Russian. We also investigate the amounts of in-domain training data needed for domain adaptation in NMT, and find a logarithmic relationship between the amount of training data and gain in BLEU score.

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Entailed Between the Lines: Incorporating Implication into NLI

cs.CL · 2025-01-13 · conditional · novelty 6.0

The paper formalizes implied entailment as a four-way NLI label, builds the INLI dataset from existing implicature sources, and shows fine-tuned models can label implied vs explicit entailment and generalize across conversational and situational domains.

citing papers explorer

Showing 1 of 1 citing paper.

  • Entailed Between the Lines: Incorporating Implication into NLI cs.CL · 2025-01-13 · conditional · none · ref 1 · internal anchor

    The paper formalizes implied entailment as a four-way NLI label, builds the INLI dataset from existing implicature sources, and shows fine-tuned models can label implied vs explicit entailment and generalize across conversational and situational domains.