Sentence generation as a planning problem
نویسندگان
چکیده
In this paper, we translate sentence generation from TAG grammars with semantic and pragmatic information into a planning problem by encoding the contribution of each word declaratively and explicitly. This allows us to tap into the recent performance improvements in off-the-shelf planners. It also opens up new perspectives on referring expression generation and the relationship between language and action.
منابع مشابه
Sentence Generation as Planning with Probabilistic LTAG
We present PCRISP, a sentence generation system for probabilistic TAG grammars which performs sentence planning and surface realization in an integrated fashion, in the style of the SPUD system. PCRISP operates by converting the generation problem into a metric planning problem and solving it using an offthe-shelf planner. We evaluate PCRISP on the WSJ corpus and identify trade-offs between cov...
متن کاملA Fuzzy Multi Objective Programming Model for Power Generation and Transmission Expansion Planning Problem
The increasing consumption of electricity over time forces different countries to establishnew power plants and transmission lines. There are various crisp single-objective mathematicalmodels in the literature for the long-term power generation and transmission expansion planning tohelp the decision makers to make more reasonable decisions. But, in practice, most of the parametersassociated wit...
متن کاملOptimization of Mixed-Integer Non-Linear Electricity Generation Expansion Planning Problem Based on Newly Improved Gravitational Search Algorithm
Electricity demand is forecasted to double in 2035, and it is vital to address the economicsof electrical energy generation for planning purposes. This study aims to examine the applicability ofGravitational Search Algorithm (GSA) and the newly improved GSA (IGSA) for optimization of themixed-integer non-linear electricity generation expansion planning (GEP) problem. The performanceindex of GEP...
متن کاملDomain proposal: Sentence generation with tree-adjoining grammars (CRISP)
Overview The CRISP domain is motivated by the problem of sentence generation in natural language generation (NLG).1 NLG is a major subfield of natural language processing, concerned with computing natural language sentences or texts that convey a given piece of information to an audience. In the sentence generation task, we focus on generating a single sentence that expresses a given meaning ac...
متن کاملFrom OpenCCG to AI Planning: Detecting Infeasible Edges in Sentence Generation
The search space in grammar-based natural language generation tasks can get very large, which is particularly problematic when generating long utterances or paragraphs. Using surface realization with OpenCCG as an example, we show that we can effectively detect partial solutions (edges) which cannot ultimately be part of a complete sentence because of their syntactic category. Formulating the c...
متن کامل