Assessing Interpretable, Attribute-related Meaning Representations for 
Adjective-Noun Phrases in a Similarity Prediction Task

Matthias Hartung

We present a distributional vector space model that incorporates Latent 
Dirichlet Allocation in order to capture the semantic relation holding 
between adjectives and nouns along interpretable dimensions of meaning: 
The meaning of adjective-noun phrases is characterized in terms of 
ontological attributes that are prominent in their compositional 
semantics. The model is evaluated in a similarity prediction task based 
on paired adjective-noun phrases from the Mitchell & Lapata (2010) 
benchmark data. Comparing our model against a high-dimensional latent 
word space, we observe qualitative differences that shed light on 
different aspects of similarity conveyed by both models and suggest 
integrating the respective models' complementary strengths.