Large, multilingual language models exhibit surprisingly good zero- or few-shot machine
translation capabilities, despite having never seen the intentionally-included translation …

This paper reviews and summarizes human evaluation practices described in 97 style transfer
papers with respect to three main evaluation aspects: style transfer, meaning preservation…

Neural sequence generation models are known to “hallucinate”, by producing outputs that
are unrelated to the source text. These hallucinations are potentially harmful, yet it remains …

We take the first step towards multilingual style transfer by creating and releasing XFORMAL,
a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, …

Detecting fine-grained differences in content conveyed in different languages matters for
cross-lingual NLP and multilingual corpora analysis, but it is a challenging machine learning …

While the field of style transfer (ST) has been growing rapidly, it has been hampered by a
lack of standardized practices for automatic evaluation. In this paper, we evaluate leading ST …

One of the core goals of Natural Language Processing (NLP) is to develop computational
representations and methods to compare and contrast text meaning across languages. Such …

A critical component in knowledge distillation is the means of coupling the teacher and student.
The predominant sequence knowledge distillation method involves supervised learning …

NLP systems have shown impressive performance at answering questions by retrieving
relevant context. However, with the increasingly large models, it is impossible and often …

This paper describes the University of Maryland’s submission to the WMT 2019 Kazakh-English
news translation task. We study the impact of transfer learning from another low-…