We introduce an architecture to learn joint multilingual sentence representations for 93
languages, belonging to more than 30 different families and written in 28 different scripts …

Word alignments are useful for tasks like statistical and neural machine translation (NMT)
and cross-lingual annotation projection. Statistical word aligners perform well, as do …

Languages differ in how they divide up the world into concepts and words; eg, in contrast to
English, Swahili has a single concept forbelly'andwomb'. We investigate these differences in …

On-device machine learning (ML) inference can enable the use of private user data on user
devices without revealing them to remote servers. However, a pure on-device solution to …

In comparative linguistics, colexification refers to the phenomenon of a lexical form
conveying two or more distinct meanings. Existing work on colexification patterns relies on …

Part-of-Speech (POS) tagging is an important component of the NLP pipeline, but many low-
resource languages lack labeled data for training. An established method for training a POS …

The manifold hypothesis suggests that word vectors live on a submanifold within their
ambient vector space. We argue that we should, more accurately, expect them to live on a …

We present a new method for sentiment lexicon induction that is designed to be applicable
to the entire range of typological diversity of the world's languages. We evaluate our method …

With the advent of end-to-end deep learning approaches in machine translation, interest in
word alignments initially decreased; however, they have again become a focus of research …

We propose a new approach for learning contextualised cross-lingual word embeddings
based on a small parallel corpus (eg a few hundred sentence pairs). Our method obtains …