Information Technology Reference
In-Depth Information
adopting the relation extraction techniques from compound noun generation works.
We are currently in the process of developing an anaphora resolution system by in-
tegrating the various relation extraction strategies described in computational works on
compound nouns.
3
Anaphora Resolution Framework
In the Introduction we stated that anaphora interpretation and noun compound gener-
ation are two indicants of the same underlying relational framework between entities.
Hence, a framework describing compound noun generation has to apply to anaphora
usage as well. In the proposed framework we extend the relations proposed for com-
pound noun generation from [18] for interpretation of noun phrase as well as pronomi-
nal anaphora.
An indirect reference such as
window
referring to
house
and
diesel
referring to
truck
is based on the predicates “house
has
windows” and “a truck
uses
diesel”. In the case
of compound noun generation, the predicate is deleted and the two entities are juxta-
posed to form the noun compounds
house window
and
diesel truck
. For interpretation
of the compound noun the consumer is expected to reconstruct the relation between the
modifier and the head noun ([6,18]). We propose that the compound noun generation
process is very similar to associative anaphora, except in the latter case the modifier is
not necessarily bound to the head noun as part of a noun compound. That is, it may
exist in another clause, however the same relation is still expected to be reconstructed
for a full interpretation of the anaphor. Hence, for the example for the predicate “house
has window”, we could have the full NP,
house window
produced by predicate deletion.
However in addition, the same predicate could also be expressed anaphorically as in the
following example:
John bought a
house
in Glen Eden.
The
windows
are wooden.
In the example above the related entities from the predicate “house has windows” are
separated into two different sentences, each expressing information about “house” and
“windows” respectively. In order to relate the two sentences we need to bridge the
“semantic gap” between “windows” and “house”. This is referred to as
text cohesion
and/or
coherence
([12,25]). Hence identifying the specific relation between an anaphor
and its antecedent is necessary for establishing coherence which is fundamental for a
full interpretation of any text.
Semantic relations between certain entities exist by default and can be assumed as
part of the lexical knowledge of the consumer. For example, the HAVE relation between
car
and
tyre
is part of lexicon so the noun compound
car tyre
and the noun
tyre
used
anaphorically to refer to
car
is readily understood. In addition, the HAVE relation can
also be established temporarily in a discourse followed by its use for anaphora and/or
compound nouns. For example, after specifying the relation “the box has tyres”, the
noun
tyres
can be used to indirectly refer to
box
in the same way as the reference of
tyres
to
car
. However, the former can only be used in the context of the discourse in which
the relation was expressed. This corresponds to Downing's [6] fortuitous relations.