How to transfer the semantic information in a sentence to a computable numerical
embedding form is a fundamental problem in natural language processing. An informative …

The rise in web and social media interactions has resulted in the efortless proliferation of
offensive language and hate speech. Such online harassment, insults, and attacks are …

Understanding human language has been a sub-challenge on the way of intelligent
machines. The study of meaning in natural language processing (NLP) relies on the …

Linguistic typology aims to capture structural and semantic variation across the world's
languages. A large-scale typology could provide excellent guidance for multilingual Natural …

Distributional semantics develops theories and methods to represent the meaning of natural
language expressions, with vectors encoding their statistical distribution in linguistic …

We present ClaimRank, an online system for detecting check-worthy claims. While originally
trained on political debates, the system can work for any kind of text, eg, interviews or …

We present LEAR (Lexical Entailment Attract-Repel), a novel post-processing method that
transforms any input word vector space to emphasise the asymmetric relation of lexical …

Average word embeddings are a common baseline for more sophisticated sentence
embedding techniques. However, they typically fall short of the performances of more …

We introduce HyperLex—a data set and evaluation resource that quantifies the extent of the
semantic category membership, that is, type-of relation, also known as hyponymy …

Semantic specialization of distributional word vectors, referred to as retrofitting, is a process
of fine-tuning word vectors using external lexical knowledge in order to better embed some …