Work

Surface Realisation from Knowledge Bases

Year: 2014

Type: dissertation

Abstract: We present a simple, data-driven approach to generation from knowledge bases (KB). A key feature of this approach is that grammar induction is driven by the extended domain of locality principle of TAG (Tree Adjoining Grammar); and that it takes into account both syntactic and semantic information. The resulting extracted TAG includes a unification based semantics and can be used by an existing surface realiser to generate sentences from KB data. Experimental evaluation on the KBGen data shows that our model outperforms a data-driven generate-and-rank approach based on an automatically induced probabilistic grammar; and is comparable with a handcrafted symbolic approach.

Source: Publications Et Travaux Academiques de Lorraine (Universite de Lorraine)

Authors: Gyawali, Bikash, Gardent, Claire

Language: English

Topic: 3D Shape Modeling and Analysis

Subfield: Computer Graphics and Computer-Aided Design

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4300064161

Cites:

Cited by: 5

Related to: 10