Luca Gilardi

University of California, Berkeley | UCB · International Computer Science Institute

Construction grammars are commonly written by hand. This is not only time and resource intensive, but also limits the potential for applications that need to extract accurate and deep semantics from real-world language. In the present paper we explore novel ways to tap into existing resources to expand Embodied Construction Grammar (ECG) semi autom...

In this chapter, we describe an implemented system for cognitively-plausible sentence interpretation called the Constructional Analyzer that leverages the power of ECG. Because the constructional analyzer employs Embodied Construction Grammar as its grammatical backbone, constructions and cognitive linguistic structures such as image schemas and fr...

Understanding cross-cultural differences has important implications for world affairs and many aspects of the life of society. Yet, the majority of text-mining methods to date focus on the analysis of monolingual texts. In contrast , we present a statistical model that simultaneously learns a set of common topics from multilingual, non-parallel dat...

Constraint satisfaction has been central to the ICSI/UC Berkeley Neural Theory of Language (NTL) project, but this aspect has not previously been emphasized. The ECG Analysis program combines constraints from several aspects of the formalism: deep semantic schemas, embodied constructions and ontological knowledge. In this chapter we focus on some a...