In this paper we present a study covering the creation of compositional distributional representations for English noun compounds (e.g. computer science) using two compositional models proposed in the literature. The compositional representations are first evaluated based on their similarity to the corresponding corpus-learned representations and then on the task of automatic classification of ...

Semantic similarity is a confidence score that replicates semantic equivalence between the meanings of two sentences. Determining the similarity among sentences is one of the critical tasks which have a wide-ranging impact in recent NLP applications. This paper presents a method for identifying semantic sentence similarity among sentences using semantic relation of word senses across the differ...

This paper focuses on the semantic relations and interpratations of Chinese noun compounds (mostly search terms). In light of the semantic classification from Semantic Knowledge-base of Contemporary Chinese (SKCC) and Qualia Structures introduced by Pustejovsky (1991, 1995), we analyze the combinations of the semantic classes of the noun compounds, and thus, discover the implicit predicates of ...

Conclusion Performance on human judgement (MC, RG, WS) and semantic relation (BLESS and SN) datasets We present a novel semantic similarity measure based on lexico-syntactic patterns such as those proposed by Hearst (1992). The measure achieves a correlation with human judgements up to 0.739. Additionally, we evaluate it on the tasks of semantic relation ranking and extraction. Our results show...

To achieve widespread acceptance, speech Understanding technology needs to be domain independent. Deep understanding, however, appears to require knowledge that is tiomain specific. Speech understanding technology, therefore, must be partitioned into domain-independent and domainspecific components. Development of domain-independent components could be promoted by creation of semantically annot...