Semantics-free

However, most of DHT systems focus strictly on handling semantics-free, large-granularity requests for objects by identifier (typically a name). They are limited to caching, pre-fetching, or pushing of content at the object level

They all try to demonstrate that language is more than just the assembling of context-free words using semantics-free rules

To date, such research has been impossible, since corpora have for the most part been annotated at a relatively shallow (semantics-free) level, forcing NLP researchers to choose between shallow approaches and hand-crafted approaches,