Enabling technology for multilingual natural language generation: the KPML development environment

By J. Bateman. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Neural Generation for Czech: Data and Baselines (2019, methodology): “There have been a few approaches using handcrafted grammars (Bateman, 1997; Allman et al., 2012).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “For example, some early systems (e.g. kpml, which we briefly discussed in the context of realisation in Section 2.6; Bateman, 1997) were based on Systemic-Functional Grammar (sfg; Halliday & Matthiessen, 2004), which can be seen as a precursor to contemporary planning-based approaches, since sfg…”
SimpleNLG: A Realisation Engine for Practical Applications (2009, background): “…has emerged over the definition of the realisation task, through the development of realisers such as REALPRO (Lavoie and Rambow, 1997), ALETHGEN (Coch, 1996), KPML (Bateman, 1997), FUF/SURGE (Elhadad and Robin, 1996), HALOGEN (Langkilde, 2000), YAG (McRoy et al., 2000), and OPENCCG (White, 2006).”
Adapting SimpleNLG to Galician language (2018, background): “Other realisers described in the literature are Alethgen (Coch, 1996), FUF/SURGE (Elhadad and Robin, 1996), Real-Pro (Lavoie and Rainbow, 1997), KPML (Bate-man, 1997), YAG (McRoy et al., 2000), HALogen (Langkilde-Geary, 2002) and OpenCCG (White, 2006).”
Hierarchical Reinforcement Learning for Adaptive Text Generation (2010, methodology): “Finally, the constructed SPL is passed to the KPML surface generator (Bateman, 1997) for string realisation.”