On Using Monolingual Corpora in Neural Machine Translation
read the original abstract
Recent work on end-to-end neural network-based architectures for machine translation has shown promising results for En-Fr and En-De translation. Arguably, one of the major factors behind this success has been the availability of high quality parallel corpora. In this work, we investigate how to leverage abundant monolingual corpora for neural machine translation. Compared to a phrase-based and hierarchical baseline, we obtain up to $1.96$ BLEU improvement on the low-resource language pair Turkish-English, and $1.59$ BLEU on the focused domain task of Chinese-English chat messages. While our method was initially targeted toward such tasks with less parallel data, we show that it also extends to high resource languages such as Cs-En and De-En where we obtain an improvement of $0.39$ and $0.47$ BLEU scores over the neural machine translation baselines, respectively.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Decomposable Neural Paraphrase Generation
DNPG is a multi-component Transformer model that disentangles paraphrase generation across granularity levels and supports unsupervised domain adaptation, claiming competitive in-domain and superior cross-domain performance.
-
LLMs and Speech: Integration vs. Combination
Tight integration of acoustic models with LLMs for ASR is ablated against shallow fusion across label units, fine-tuning strategies, LLM sizes, and joint CTC decoding to mitigate hallucinations.
-
Non-Intrusive Automatic Speech Recognition Refinement: A Survey
A survey that classifies non-intrusive ASR refinement methods into five categories, reviews domain adaptation and evaluation datasets, proposes standardized metrics, and identifies future research directions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.