|In other news
Members of the EMBEDDIA consortium met with representatives from the Croatian media 24sata in November and presented our tools and solutions for some of the issues faced by the members of their newsroom. More information here.
Some of our recent scientific publications
- Recycling a genre for news automation: The production of Valtteri the Election Bot
"The amount of available digital data is increasing at a tremendous rate. These data, however, are of limited use unless converted into a user-friendly form. We took on this task and built a natural language generation (NLG) driven system that generates journalistic news stories about elections without human intervention."
Authors: Lauri Haapanen, Leo Leppänen
- Bisociative Literature-Based Discovery: Lessons Learned and New Word Embedding Approach
"This paper outlines several outlier-based literature mining approaches to bridging term detection and the lessons learned from selected biomedical literature-based discovery applications. The paper addresses also new prospects in bisociative literature-based discovery, proposing an advanced embeddings-based technology for cross-domain literature mining."
Authors: Nada Lavrač, Matej Martinc, Senja Pollak, Maruša Pompe Novak, Bojan Cestnik
- How Furiously Can Colorless Green Ideas Sleep? Sentence Acceptability in Context
"We compare the acceptability ratings of sentences judged in isolation, with a relevant context, and with an irrelevant context. Our results show that context induces a cognitive load for humans, which compresses the distribution of ratings. Next, we test unidirectional and bidirectional language models in their ability to predict acceptability ratings. The two sets of experiments provide insights into the cognitive aspects of sentence processing and central issues in the computational modeling of text and discourse."
Authors: Jey Han Lau, Carlos Armendariz, Shalom Lappin, Matthew Purver, Chang Shu