Adjective based inference

Amoia, Marilisa; Gardent, Claire

doi:10.3115/1641493.1641498

Cited by 7 publications

(13 citation statements)

References 7 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the hierarchical classification of adjectives described above is widely accepted and often applied in NLP tasks (Amoia and Gardent, 2006;Amoia and Gardent, 2007;Boleda et al, 2012;McCrae et al, 2014), it is not undisputed. Some linguists take the position that in fact privative ad-jectives are simply another type of subsective adjective (Partee, 2003;McNally and Boleda, 2004;Abdullah and Frost, 2005;Partee, 2007).…”

Section: Background and Related Workmentioning

confidence: 99%

“…This generalization has prompted normative rules for the treatment of such adjectives in various NLP tasks. In information extraction, it is assumed that systems cannot extract useful rules from sentences containing non-subsective modifiers (Angeli et al, 2015), and in RTE, it is assumed that systems should uniformly penalize insertions and deletions of non-subsective adjectives (Amoia and Gardent, 2006). On further analysis, we reveal that, when adjectives do behave non-subsectively, they often exhibit asymmetric entailment behavior in which insertion leads to contradictions (ID ⇒ ¬ fake ID) but deletion leads to entailments (fake ID ⇒ ID).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

So-Called Non-Subsective Adjectives

Pavlick¹,

Callison-Burch²

2016

Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics

View full text Add to dashboard Cite

The interpretation of adjective-noun pairs plays a crucial role in tasks such as recognizing textual entailment. Formal semantics often places adjectives into a taxonomy which should dictate adjectives' entailment behavior when placed in adjective-noun compounds. However, we show experimentally that the behavior of subsective adjectives (e.g. red) versus non-subsective adjectives (e.g. fake) is not as cut and dry as often assumed. For example, inferences are not always symmetric: while ID is generally considered to be mutually exclusive with fake ID, fake ID is considered to entail ID. We discuss the implications of these findings for automated natural language understanding.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

So-Called Non-Subsective Adjectives

Pavlick¹,

Callison-Burch²

2016

Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics

View full text Add to dashboard Cite

show abstract

“…Tien Nguyen et al (2014) look at the adjectives in the restricted domain of computer vision. Other past work has employed first-order logic and other formal representations of adjectives in order to provide compositional entailment predictions (Amoia and Gardent, 2006;Amoia and Gardent, 2007;McCrae et al, 2014). Although theoretically appealing, such rigid logics are unlikely to provide the flexibility needed to handle the type of common-sense inferences we have discussed here.…”

Section: Related Workmentioning

confidence: 99%

Most "babies" are "little" and most "problems" are "huge": Compositional Entailment in Adjective-Nouns

Pavlick¹,

Callison-Burch²

2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

We examine adjective-noun (AN) composition in the task of recognizing textual entailment (RTE). We analyze behavior of ANs in large corpora and show that, despite conventional wisdom, adjectives do not always restrict the denotation of the nouns they modify. We use natural logic to characterize the variety of entailment relations that can result from AN composition. Predicting these relations depends on context and on commonsense knowledge, making AN composition especially challenging for current RTE systems. We demonstrate the inability of current stateof-the-art systems to handle AN composition in a simplified RTE task which involves the insertion of only a single word.

show abstract

“…Still, these classifications do not clearly separate meaning and syntax and also require a separate modelling of comparatives and class-specific meanings for many adjectives. Amoia and Gardent (2006) handled the problem of adjectives in the context of textual entailment. They analyzed 15 classes that show the subtle interaction between the semantic class (e.g., 'privative') and the issues of attributive/predicative use and gradability.…”

Section: Related Workmentioning

confidence: 99%

Modelling the Semantics of Adjectives in the Ontology-Lexicon Interface

McCrae

Quattri

Unger

et al. 2014

Proceedings of the 4th Workshop on Cognitive Aspects of the Lexicon (CogALex)

View full text Add to dashboard Cite

The modelling of the semantics of adjectives is notoriously challenging. We consider this problem in the context of the so called ontology-lexicon interface, which attempts to capture the semantics of words by reference to an ontology in description logics or some other, typically first-order, logical formalism. The use of first order logic (hence also description logics), while effective for nouns and verbs, breaks down in the case of adjectives. We argue that this is primarily due to a lack of logical expressivity in the underlying ontology languages. In particular, beyond the straightforward intersective adjectives, there exist gradable adjectives, requiring fuzzy or non-monotonic semantics, as well as operator adjectives, requiring second-order logic for modelling. We consider how we can extend the ontology-lexicon interface as realized by extant models such as lemon in the face of the issues mentioned above, in particular those arising in the context of modelling the ontological semantics of adjectives. We show how more complex logical formalisms that are required to capture the ontological semantics of adjectives can be backward engineered into OWL-based modelling by means of pseudo-classes. We discuss the implications of this modelling in the context of application to ontology-based question answering.

show abstract

Adjective based inference

Cited by 7 publications

References 7 publications

So-Called Non-Subsective Adjectives

So-Called Non-Subsective Adjectives

Most "babies" are "little" and most "problems" are "huge": Compositional Entailment in Adjective-Nouns

Modelling the Semantics of Adjectives in the Ontology-Lexicon Interface

Contact Info

Product

Resources

About