The number of scientific publications in the literature is steadily growing, containing our
knowledge in the biomedical, health, and clinical sciences. Since there is currently no …

Word embeddings are vectorial semantic representations built with either counting or
predicting techniques aimed at capturing shades of meaning from word co-occurrences …

A hallmark of human intelligence is the ability to adapt to new situations by applying learned
rules to new content (systematicity) and thereby enabling an open-ended number of …

Anomaly detection in process mining aims to recognize outlying or unexpected behavior in
event logs for purposes such as the removal of noise and identification of conformance …

Causationin written natural language can express a strong relationship between events and
facts. Causation in the written form can be referred to as a causal relation where a cause …

Cross-document event coreference resolution (CDCR) is an NLP task in which mentions of
events need to be identified and clustered throughout a collection of documents. CDCR …

It is well-known that derivational affixes can be highly polysemous, producing a range of
different, often related, meanings. For example, English deverbal nouns with the suffix-er …

We consider the semantics of prepositions, revisiting a broad-coverage annotation scheme
used for annotating all 4,250 preposition tokens in a 55,000 word corpus of English …

Representing snippets of information abstractly is a task that needs to be performed for
various purposes, such as database view specification and the first stage in the natural …

Semantic relations are often signaled with prepositional or possessive marking--but extreme
polysemy bedevils their analysis and automatic interpretation. We introduce a new …