SentiLecto is Natural Tech's NLU engine. This Entity-based Sentiment Analysis solution yields a highly fine-grained representation for the sentiment values involved in each opinion. Unlike other approaches, this solution can deal with polarity shifting in the same sentence ('I like chocolate but I hate strawberry ice-cream'), within embedded clauses ('Norwegians, who are an aggresive People, export the exquisite herring'), or even onto the very same word ('Somebody who wasted a chance to do something' means that person did something bad about something good). SentiLecto better represents the premise whereby the entities involved in the opinion are syntactically mapped onto SVO (subject-verb-object) slots for their sentiment assignments: 'Mary hates John' (2 entities but only the object has a negative presentation) vs. 'Mary defames John' (the same 2 entities but only the subject has negative presentation).

SentiLecto leans on outstanding linguistic features such as: passive/active voice transformation, negation scope, anaphora resolution and co-reference chains, ellipsis, modality treatment, semantic features (animity and others) and accurate verbal frames for all Spanish verbs, even with 'se-impersonal' usages ('se mostraron retratos' = 'alguien mostró retratos' = 'somebody showed portraits'), 'se-clitic' usages (for example, plain action 'mostrar' 'to show something' vs. 'mostrarSE' 'to show yourself, namely to feel some way before a situation').

It can recognize & classify named-entities (NERC) with identity matching. Also, SentiLecto can identify whether or not an utterance is a real fact (fact mining), normalizing facts through deep understanding of syntax and semantics.