The First Surface Realisation Shared Task: Overview and Evaluation Results

By Anya Belz, Michael. White, Dominic Espinosa, Eric Kow, Deirdre Hogan, Amanda Stent. 2011

109 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

The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics (2021, neutral): “SR’11, SR’18, SR’19 (Belz et al., 2011; Mille et al., 2018, 2019) 25.”
Creating Training Corpora for NLG Micro-Planners (2017, methodology): “NLG benchmarks have also been proposed where the input data is either derived from dependency parse trees (SR’11 task, (Belz et al., 2011)) or constructed through manual annotation (AMR Corpus (Banarescu et al.”
The WebNLG Challenge: Generating Text from RDF Data (2017, background): “Previous Natural Language Generation (NLG) challenges have focused on surface realisation (Banik et al., 2013; Belz et al., 2011), referring expression generation (Belz and Gatt, 2007; Gatt et al.”
Overcoming the Lack of Parallel Data in Sentence Compression (2013, background): “The solution to the surface realization problem (Belz et al., 2011) is standard: the words in the compression subtree are put in the same order they are found in the source.”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “…(2014) observe that, despite many realisers being evaluated against the Penn Treebank, they make different assumptions about the input format, including how detailed the pre-syntactic input representation is, a problem also observed in the first Surface Realisation shared task (Belz et al., 2011).”
Analysing Data-To-Text Generation Benchmarks (2017, background): “the surface realisation shared-task (Belz et al., 2011)) or domain (Wen et al.”
Deep Graph Convolutional Encoders for Structured Data to Text Generation (2018, methodology): “graph (Belz et al., 2011), namely the SR11Deep generation task.”
The First Multilingual Surface Realisation Shared Task (SR’18): Overview and Evaluation Results (2018, methodology): “Slider design: In SR’11, a slider design was used, which had a smiley face at the 100 end and a frowning face at the 0 end, with the pointer starting out at 50.”
Generation from Abstract Meaning Representation using Tree Transducers (2016, methodology): “Statistical NLG systems have been built for input representations such as HPSG (Nakanishi et al., 2005), LFG (Cahill and Van Genabith, 2006; Hogan et al., 2007), and CCG (White et al., 2007), as well as surface and deep syntax (Belz et al., 2011).”
The KBGen Challenge (2013, methodology): “The KBGen task provides a framework for NLG evaluation which is similar to but different from the Surface Realisation (SR) Task (Belz et al., 2011).”
FORGe at SemEval-2017 Task 9: Deep sentence generation based on a sequence of graph transducers (2017, methodology): “The surface-syntactic structures are linearized with an off-the-shelf tool used in the first SRST (Belz et al., 2011), a statistical tree linearizer”
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures (2019, unknown): “In comparison with other popular NLG benchmarks (Belz et al., 2011; Novikova et al., 2017; Mille et al., 2018), WebNLG is the most semantically varied corpus, consisting of 25,298 texts describing 9,674 sets of up to 7 RDF triples in 15 domains.”
The Third Multilingual Surface Realisation Shared Task (SR’20): Overview and Evaluation Results (2020, methodology): “When we ran the first Surface Realisation Shared Task in 2011 (Belz et al., 2011), it was to address a situation where there were many different approaches to SR but none of them were comparable.”