Towards more variation in text generation: Developing and evaluating variation models for choice of referential form

By Thiago Castro Ferreira, Emiel Krahmer, Sander Wubben. 2016

30 citations recorded by the source corpus.

In this study, we introduce a nondeterministic method for referring expression generation. We describe two models that account for individual variation in the choice of referential form in automatically generated text: a Naive Bayes model and a Recurrent Neural Network. Both are evaluated using the VaREG corpus. Then we select the best performing model to generate referential forms in texts from the GREC-2.0 corpus and conduct an evaluation experiment in which humans judge the coherence and comprehensibility of the generated texts, comparing them both with the original references and those produced by a random baseline model.

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

The WebNLG Challenge: Generating Text from RDF Data (2017, methodology): “Missing entities were added using a referring expression generation module (Castro Ferreira et al., 2016).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “…more appreciated by readers than variation in weather reports (on which see Reiter et al., 2005); it may also depend on where in a text the variation occurs (e.g., variation in expressing timestamps may be less appreciated than variation in referential forms, see e.g., Ferreira et al. (2016)).”
Talking about other people: an endless range of possibilities (2018, background): “Natural Language Generation researchers tasked with describing other people have mostly been concerned with generating referring expressions without visual context, usually for well-known entities (e.g. Castro Ferreira et al. 2016; Kutlak et al. 2016).”
Non-neural Models Matter: a Re-evaluation of Neural Referring Expression Generation Systems (2022, methodology): “The definition of each criterion was taken from Castro Ferreira et al. (2018a).”
Measuring the Diversity of Automatic Image Descriptions (2018, background): “Castro Ferreira et al. (2016) focused on the deterministic nature of NLG systems, in the sense that they repeatedly use the same referential forms to refer to the same entity in longer stretches of text.”
RDF2PT: Generating Brazilian Portuguese Texts from RDF Data (2018, methodology): “alize all the verbs in the past tense. 11See the complete list of dependency parsing tags in Ngonga Ngomo et al. (2013). 4. Evaluation We based our evaluation methodology on Gardent et al. (2017) and Ferreira et al. (2016). Our main goal was to evaluate how well RDF2PT represents the information obt”