The performance of neural machine translation (NMT) systems only trained on a single language variant degrades when confronted with even slightly different language variations. With this work, we build upon previous work to explore how to mitigate …
NLP systems are typically trained and evaluated in “clean” settings, over data without significant noise. However, systems deployed in the real world need to deal with vast amounts of noise. At GMU NLP we work towards making NLP systems more robust to several types of noise (adversarial or naturally occuring).
The quality of Neural Machine Translation (NMT) has been shown to significantly degrade when confronted with source-side noise. We present the first large-scale study of state-of-the-art English-to-German NMT on real grammatical noise, by evaluating …
We share the findings of the first shared task on improving robustness of Machine Translation (MT). The task provides a testbed representing challenges facing MT models deployed in the real world, and facilitates new approaches to improve models′ …
While neural machine translation (NMT) achieves remarkable performance on clean, in-domain text, performance is known to degrade drastically when facing text which is full of typos, grammatical errors and other varieties of noise. In this work, we …
Neural Machine Translation (NMT) systems are known to degrade when confronted with noisy data, especially when the system is trained only on clean data. In this paper, we show that augmenting training data with sentences containing …