Computational Intelligence - February 2014 - 26

e1 p2

x0
(

colonel(x0)

A say(e1)
Agent(e1, x0)
Topic(e1, p2)

p2:

)

x3 x4 x5 x6 e7
lose(e7)
drug(x4)
nn(x4, x3)
dealer(x3)
Wx5W = 3600
kilo(x5)
narcotic(x6)
of(x5, x6)
Agent(e7, x3)
Theme(e7, x5)

Figure 6 The output of Boxer for the sentence "Drug dealers have
lost some 3,600 kilos of narcotics, the colonel said".

opinion and sentiment mining: attribute detection, situation
modeling, negation and modality representation. FRED is in
charge of processing Boxer output, and of producing its RDF/
OWL representation: Figure 7 shows the semantic representation of the sample sentence as it is provided by FRED6.
FRED recognizes and represents two main event occurrences
in this sentence, i.e. fred:say_1,7 and fred:lose_1. For
each of them it provides a type and identifies its participating
entities, e.g. fred:colonel_1 participates in fred:say_1
with the role of agent8. Each entity is assigned with a type and
aligned, if possible, to an existing Semantic Web entity, e.g. an
entity from a Linked Data dataset, e.g. DBpedia, WordNet, etc. In
order to obtain a form compliant to Semantic Web modeling
from Boxer output we perform a number transformations e.g.,
the variables from Boxer output are either eliminated, or transformed into new individuals, when they refer to actual entities in
discourse representation; the p2 proposition is interpreted as a
"situation" that is eventually resolved to its main contained event
(fred:lose_1); the "drug" and "dealer" predicates are composed in the new class fred:DrugDealer, with a subclass axiom to
fred:Dealer, etc.
4.1. Opinion Model Annotator

formal theory of meaning originally described in [22]. It provides an event-based model to represent natural language, and is
compatible with first-order logic (FOL). DRT uses an explicit
semantic structured language called Discourse Representation
Structure (DRS). In Boxer, DRS are enriched with the VerbNet
[35] inventory of thematic roles. Boxer uses thousands of heuristic rules to transform C&C trees into logical DRS representations. Figure 6 shows the output of Boxer for our sample sentence. The first box introduces a first existential quantification
on a variable that is predicated as "colonel", while the second
box contains a new event predicated variable ("say(e1)"), and
two semantic roles declarations, one of which has an embedded
proposition "p2" as arguments. The referent of the p2 variable is
a box that contains the bulk of Boxer's representation, with
more variables predications, semantic roles, and co-references.
In [33] we have presented FRED,5 a tool that formally maps
DRT logical forms (DRS) to RDF/OWL by exploiting framebased design, and by implementing a set of heuristics that
address terminology and structure generation according to
Semantic Web design practices. FRED enables the semantic representation of opinion sentences according to the frame-based
model described in Section 3.1. FRED heuristics are designed
to take into account the semantic interpretation of language
when transforming it to a formalized form. It addresses, besides
sense tagging (to associate a type to a certain entity), sense disambiguation (to identify the correct sense of a term given a certain context), semantic role labeling (to assign a thematic role to
an entity, in the context of an event it participates in), terminology extraction and composition, taxonomy induction, named
entity resolution, etc., and also issues that are important for
5

http://wit.istc.cnr.it/stlab-tools/fred

IEEE ComputatIonal IntEllIgEnCE magazInE | FEbruary 2014

On top of FRED, we have developed an opinion model annotator
[37], a component that implements a set of heuristics that
extract, from the FRED's graph of a given sentence, information about holders of an opinion sentence, its topics, and its
opinion expressing words (i.e., opinion features). Sentilo
enriches the RDF/OWL semantic representation of an opinion sentence with annotation triples based on our opinion
model (cf. Section 3.2).
Holder Detection
To detect opinion holders we rely on Levin opinion (cf. Figure 8),
a revision of Levin's classification of verbs [27; 38]: we have classified four classes of opinion verbs that imply the presence of an
holder; we call them opinion trigger verbs. It is possible to download the four categories of verbs from [32]. Figure 8 specifies the
relationship between different verb categories (referring to
Levin's classification) depending on the presence of an holder
which is stating or denying a fact, or if they imply a positive sentiment. When a trigger verb is not present in a sentence, the
holder is assumed to be implicit (e.g. the author of the sentence).
The four classes of trigger verbs can be described as follows:
❏ Holder activation verbs: verbs such as accept, agree, think, say, tell,
cite, claim, recognize, etc. which indicate the presence of an
opinion holder who is the subject of the underlying verb;
subjects of such verbs are a affirming something expressed
in the opinionated context. Verbs in this class appear in the
opinion trigger context described in Section 3.2;
6

We have removed part of the graph for space reason, the reader is welcome to submit
the sentence to FRED or Sentilo online to see the complete output.
7
fred: prefix is the local namespace of the RDF graph produced by FRED.
8
vn.role: stands for http://www.ontologydesignpatterns.org/ont/vn/abox/role/.
Thematic roles are based on VerbNet [5].

http://www.ontologydesignpatterns.org/ont/vn/abox/role/

Table of Contents for the Digital Edition of Computational Intelligence - February 2014