Annotating Underquantification
Aurélie Herbelot, Ann Copestake · 2010
Many noun phrases in text are ambiguously quantified: syntax doesn’t explicitly tell us whether they refer to a single entity or to several, and what portion of the set denoted by the Nbar actually takes part in the event expressed by the verb. We describe this ambiguity phenomenon in terms of underspecification, or rather underquantification. We attempt to validate the underquantification hypothesis by producing and testing an annotation scheme for quantification resolution, the aim of which is to associate a single quantifier with each noun phrase in our corpus. 1 Quantification resolution We are concerned with ambiguously quantified noun phrases (NPs) and their interpretation, as illustrated by the following examples: 1. Cats are mammals = All cats... 2. Cats have four legs = Most cats... 3. Cats were sleeping by the fire = Some cats... 4. The beans spilt out of the bag = Most/All of the beans... 5. Water was dripping through the ceiling = Some water... We are interested in quantification resolution, that is, the process of giving an ambiguously quantified NP a formalisation which expresses a unique set relation appropriate to the semantics of the utterance. For instance, we wish to arrive at: 6. All cats are mammals. |φ∩ψ | = |φ | where φ is the set of all cats and ψ the set of all mammals. Resolving the quantification value of NPs is important for many NLP tasks. Let us imagine an information extraction system having retrieved the triples ‘cat – is – mammal ’ and ‘cat – chase –