The aNALoGuE Challenge: Non Aligned Language GEneration
By Jekaterina Novikova, Verena Rieser. 2016
9 citations recorded by the source corpus.
We propose a shared task based on recent advances in learning to generate natural language from meaning representations using semantically unaligned data. The aNALoGuE challenge aims to evaluate and compare recent corpus-based methods with respect to their scalability to data size and target complexity, as well as to assess predictive quality of automatic evaluation metrics.
Subfields: Artificial Intelligence
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
- Ondrej Dusek
- Verena Rieser
- Jekaterina Novikova
- Emiel Krahmer
- Claire Gardent
- Albert Gatt
- Laura Perez-Beltrachini
- Elizabeth Clark
Citations in the corpus
- Creating Training Corpora for NLG Micro-Planners (2017, neutral): “Similarly, Novikova and Rieser (2016) described a framework for collecting data-text pairs using automatic quality control measures and evaluating how the type of the input representations (text vs pictures) impacts the quality of crowdsourced text.”
- Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, background): “This paper provides a comprehensive final report and extended analysis of the first shared task on End-to-End (E2E) Natural Language Generation (NLG), substantially extending previous reports (Novikova and Rieser, 2016; Novikova et al., 2017b; Dušek et al., 2018).”
- Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “Recent proposals for new challenges extend these to narrative generation (Concepción et al., 2016), generation from structured web data (Colin et al., 2016) and from unaligned pairs of meaning representations and text (Novikova & Rieser, 2016a).”
- Analysing Data-To-Text Generation Benchmarks (2017, methodology): “The other two datasets were created manually with humans providing text for dialogue acts in the case of (Wen et al., 2015b; Wen et al., 2016)’s RNNLG datasets (laptop, TV, hotel, restaurant) and image descriptions in the case of (Novikova and Rieser, 2016)’s dataset ( I MAGE D ESC ).”