Influence of personal choices on lexical variability in referring expressions

Abstract

Variability is inherent in human language as different people make different choices when facing the same communicative act. In Natural Language Processing, variability is a challenge. It hinders some tasks such as evaluation of generated expressions, while it constitutes an interesting resource to achieve naturalness and to avoid repetitiveness. In this work, we present a methodological approach to study the influence of lexical variability. We apply this approach to TUNA, a corpus of referring expression lexicalizations, in order to study the use of different lexical choices. First, we reannotate the TUNA corpus with new information about lexicalization, and then we analyze this reannotation to study how people lexicalize referring expressions. The results show that people tend to be consistent when generating referring expressions. But at the same time, different people also share certain preferences.

Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation

“…For instance, Bohnet (2008) and Di Fabbrizio et al (2008) explore statistical methods to learn individual preferences for particular attributes, a strategy also used by Viethen and Dale (2010). Hervás et al (2013) use case-based reasoning to inform lexical choice when realising a set of semantic attributes for a referring expression, where the case base differentiates between authors in the corpus to take individual lexicalisation preferences into account (see also Hervás et al, 2016).…”

Generating natural language descriptions using speaker-dependent information

“…In Natural Language Generation systems, the computational task of referring expression generation (REG) concerns the production of linguistic forms that uniquely describe – or refer to – a given target object (Krahmer and van Deemter 2012). REG usually involves two subtasks: content selection (i.e., deciding ‘what to say’), and surface realisation (i.e., deciding ‘how to say it’ in a target language) (Hervás et al 2016). In this paper, we will focus on the former, discussing how to determine the semantic contents of definite descriptions as in ‘the man sitting next to the door’, ‘the large black hound’, ‘the small white church on 15th st.’, etc.…”