Broad Coverage Multilingual Deep Sentence Generation with a Stochastic Multi-Level Realizer

By Bernd Bohnet, Leo Wanner, Simon Mille, Alicia Burga. 2010

61 citations recorded by the source corpus.

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, background): “Bohnet et al. (2010) created the ﬁrst statistical multilingual re-alizer based on a pipeline of SVMs, the recent surface realization challenge (Mille et al., 2018) then features further fully trainable realizers tested on multiple languages, including neural models.”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “Bohnet et al. (2010) describe a realiser using underspecified dependency structures as input, in a framework based on Support Vector Machines, where classifiers are organised in a cascade.”
Training a Natural Language Generator From Unaligned Data (2015, methodology): “While dependency-based deep syntax has been used previously in statistical NLG, the approaches known to us (Bohnet et al., 2010; Belz et al., 2012; Ballesteros et al., 2014) focus only on the surface realization step and do not include a sentence plan-458 ner, whereas our work is mainly focused on…”
Generation from Abstract Meaning Representation using Tree Transducers (2016, unknown): “The deep syntax representations in Bohnet et al. (2010) and Belz et al. (2011) share similarities with AMR: the representations are graphs with re-entrancies, and have an concept inventory from PropBank (Palmer et al., 2005).”
Discriminative Syntax-Based Word Ordering for Text Generation (2015, unknown): “There is a recent line of research on text-to-text generation, which studies the linearization of dependency structures (Barzilay and McKeown 2005; Filippova and Strube 2007, 2009; He et al. 2009; Bohnet et al. 2010; Guo, Hogan, and van Genabith 2011).”
The First Surface Realisation Shared Task: Overview and Evaluation Results (2011, methodology): “The deep representation is derived from the merged Nombank, Propbank and syntactic dependencies in a process similar to the graph completion algorithm outlined in (Bohnet et al., 2010) (see Section 2.”