Hannu Toivonen


pdf bib
Unsupervised Learning of Cross-Lingual Symbol Embeddings Without Parallel Data
Mark Granroth-Wilding | Hannu Toivonen
Proceedings of the Society for Computation in Linguistics (SCiL) 2019


pdf bib
Data-Driven News Generation for Automated Journalism
Leo Leppänen | Myriam Munezero | Mark Granroth-Wilding | Hannu Toivonen
Proceedings of the 10th International Conference on Natural Language Generation

Despite increasing amounts of data and ever improving natural language generation techniques, work on automated journalism is still relatively scarce. In this paper, we explore the field and challenges associated with building a journalistic natural language generation system. We present a set of requirements that should guide system design, including transparency, accuracy, modifiability and transferability. Guided by the requirements, we present a data-driven architecture for automated journalism that is largely domain and language independent. We illustrate its practical application in the production of news articles about the 2017 Finnish municipal elections in three languages, demonstrating the successfulness of the data-driven, modular approach of the design. We then draw some lessons for future automated journalism.


pdf bib
“Let Everything Turn Well in Your Wife”: Generation of Adult Humor Using Lexical Constraints
Alessandro Valitutti | Hannu Toivonen | Antoine Doucet | Jukka M. Toivanen
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)