BERTTune: Fine-Tuning Neural Machine Translation with BERTScore

Abstract

Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on the recently-proposed BERTScore evaluation metric. BERTScore is a scoring function based on contextual embeddings that overcomes the typical limitations of n-gram-based metrics (e.g. synonyms, paraphrases), allowing translations that are different from the references, yet close in the contextual embedding space, to be treated as substantially correct. To be able to use BERTScore as a training objective, we propose three approaches for generating soft predictions, allowing the network to remain completely differentiable end-to-end. Experiments carried out over four, diverse language pairs have achieved improvements of up to 0.58 pp (3.28%) in BLEU score and up to 0.76 pp (0.98%) in BERTScore (F BERT ) when finetuning a strong baseline.

SE‐Former: Incorporating sentence embeddings into Transformer for low‐resource NMT

“…MASS allows the decoder to predict successive sequence fragments to improve the decoder's language modelling capabilities. On the other hand, finetune the strong NMT baseline with BertScore can amend overfitting and effectively overcome the typical limitations of n-gram matching [9], they use BertScore as the objective function for fine-tuning. Wei et al [10] leverage a pre-trained Transformer encoder based on contrastive learning to enrich the representations of bilingual.…”

Self-powered Vs. high speed ZnO-based photodetectors

“…Various methods have been proposed to tackle this problem (Pan et al, 2023). From training-time correction Li et al, 2019;Jauregi Unanue et al, 2021;Zelikman et al, 2022;Huang et al, 2022) to post output generation refinement (Madaan et al, 2023;Shinn et al, 2023;Zhang et al, 2023;Pan et al, 2023;Yu et al, 2023;Gou et al, 2023;Paul et al, 2023;Akyurek et al, 2023), these methods have shown the impact that iterative self-refinement and proper feedback can have on the performance of LLMs.…”