Choosing words in computer-generated weather forecasts

By Ehud Reiter, Somayajulu Gowri Sripada, J. Hunter, Jin Yu, Ian P. Davy. 2005

293 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Natural Language Generation

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

In Natural Language Generation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, background): “…et al., 1998; Chen and Mooney, 2008; Wiseman et al., 2017; Wang, 2019; Taniguchi et al., 2019), weather forecasts (Goldberg et al., 1994; Reiter et al., 2005; Liang et al., 2009; Konstas and Lapata, 2012; Mei et al., 2016), biographical texts (Lebret et al., 2016; Sha et al., 2018; Liu…”
Challenges in Data-to-Document Generation (2017, methodology): “…1992; Reiter and Dale, 1997; Duboue and McKeown, 2003; Barzilay and Lapata, 2005), and surface realization (“how to say it”) (Goldberg et al., 1994; Reiter et al., 2005) with earlier work using (hand-built) grammars, and later work using SMT-like approaches (Wong and Mooney, 2007) or…”
Neural Text Generation from Structured Data with Application to the Biography Domain (2016, background): “Traditionally, generation systems relied on rules and hand-crafted speciﬁcations (Dale et al., 2003; Reiter et al., 2005; Green, 2006; Galanis and Androut-1 sopoulos, 2007; Turner et al., 2010).”
Semantic Parsing via Paraphrasing (2014, background): “Research on generation (Dale et al., 2003; Reiter et al., 2005; Turner et al., 2009; Piwek and Boyer, 2012) typically focuses on generating natural utterances for human consumption, where ﬂuency is important.”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “Thus, in a user-oriented evaluation, the SumTimemousam system weather forecasts were preferred by readers over those written by forecasters because the latter’s lexicalisation decisions were susceptible to apparently arbitrary variation (Reiter et al., 2005); similar outcomes were more recently repo”
Analysing Data-To-Text Generation Benchmarks (2017, background): “In some scenarios, generation datasets provide linguistic descriptions of a speciﬁc domain and application (e.g. (Reiter et al., 2005)).”
Generating Text from Structured Data with Application to the Biography Domain (2016, background): “Traditionally, generation systems relied on rules and hand-crafted speciﬁcations (Dale et al., 2003; Reiter et al., 2005; Green, 2006; Galanis and An-droutsopoulos, 2007; Turner et al., 2010).”
Comparing Rating Scales and Preference Judgements in Language Evaluation (2010, background): “Binary preference judgements have been used in NLP system evaluation (Reiter et al., 2005), but to our knowledge this is the ﬁrst systematic investigation of preference-strength judgements where evaluators express, in addition to their preference ( which system do you prefer?”
Table-to-Text: Describing Table Region With Natural Language (2018, methodology): “Our work relates to existing studies that generate natural language sentence from structured data (Barzilay and Lapata 2005; Reiter et al. 2005; Angeli, Liang, and Klein 2010; Konstas and Lapata 2012; Androutsopoulos, Lampouras, and Galanis 2013).”
Mapping the field of Algorithmic Journalism (2016, methodology): “A popular application of NLG was textual weather forecasting, e.g. FOG (Goldberg, Driedger, and Kittredge 1994) or SumTime (Reiter et al. 2005).”
Imitation learning for language generation from unaligned data (2016, background): “…resources (i.e. sentence plans, aggregation rules, ordering information, etc.) to be manually authored for a particular task, e.g. weather reporting (Reiter et al., 2005), route navigation (Dale et al., 2003), or ontology descriptions (Bontcheva and Wilks, 2004; Androutsopoulos et al., 2013).”
SimpleNLG: A Realisation Engine for Practical Applications (2009, unknown): “For example, the language used in summaries of weather data (Reiter et al., 2005) or patient information (Portet et al., to appear) differs from standard usage, and does not always allow variation to the same extent.”
A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems (2020, background): “In the context of evaluating accuracy, human evaluators are usually asked to assess the overall accuracy of a generated text (Reiter and Belz, 2009), or to compare two texts and say which text is overall most accurate (Reiter et al., 2005; Novikova et al., 2018).”
Automated Crowdturfing Attacks and Defenses in Online Review Systems (2017, methodology): “There are a number of natural language generation techniques based on pre-defined templates [57, 58, 70].”
Order-Planning Neural Text Generation From Structured Data (2017, background): “Text generation has long aroused interest in the NLP community due to is wide applications including automated navigation (Dale, Geldof, and Prost 2003) and weather forecasting (Reiter et al. 2005).”
Comparing Automatic and Human Evaluation of NLG Systems (2006, methodology): “S UMTIME generates very high-quality texts, in some cases forecast users believe S UMTIME texts are better than human-written texts (Reiter et al., 2005).”
Unsupervised Concept-to-text Generation with Hypergraphs (2012, methodology): “A common modeling strategy is to break up the generation process into a sequence of local decisions, each learned separately (Reiter et al., 2005; Belz, 2008; Chen and Mooney, 2008; Angeli et al., 2010; Kim and Mooney, 2010).”
Text Generation with Exemplar-based Adaptive Decoding (2019, unknown): “There are, of course, many other strategies to get the exemplars, e.g., using handcrafted or heuristically created hard templates (Reiter et al., 2005; Becker, 2002; Foster and White, 2004, inter alia ), randomly sampling multiple training instances (Guu et al., 2018), or learning a neural reranker…”