Paying Heed to Collocations

Abstract

In this paper, we introduce a system, Sentence Planning Using Description, which generates collocations within the paradigm of sentence planning. SPUD simultaneously constructs the semantics and syntax of a sentence using a Lexicalized Tree Adjoining Grammar (LTAG). This approach captures naturally and elegantly the interaction between pragmatic and syntactic constraints on descriptions in a sentence, and the inferential and lexical interactions between multiple descriptions in a sentence, At the same time, it exploits linguistically motivated, declarative specifications of the discourse functions of syntactic constructions to make contextually appropriate syntactic choices.

AutoBrief: an experimental system for the automatic generation of briefings in integrated text and information graphics

“…Unfortunately, this may result in more verbose noun phrases. A text generator can produce more concise output by reasoning about what inferences the audience can derive from its output (Stone and Doran, 1996). Although the input to each of AutoBrief's text and graphics generators is encoded in a logic-based plan content language, neither generator adopts a logical inference based approach.…”

Microplanning with Communicative Intentions: The SPUD System

“…Our generator, called SPUD (for sentence planning using description), maintains a common representation of its provisional utterance during microplanning and carries out a single decision-making strategy using this representation. In what follows, we draw on and extend our preliminary presentations of SPUD in (Stone and Doran, 1996;Stone and Doran, 1997;Stone and Webber, 1998;Stone et al, 2000) to describe this approach in more detail.…”

Sentence planning as description using tree adjoining grammar

“…figure 7). (Stone and Doran, 1996), we use reference to properties, actions and belief contexts (Ballim et al, 1991) to describe semantic collocations (Pustejovsky, 1991) and idiomatic composition (Nunberg et al, 1994).…”

“…This means that the algorithm generates the most marked licensed form. In (Stone and Doran, 1996) we explore the use of additional factors, such as attentional state and lexical preferences, in this step.…”