no code implementations • 24 Jul 2023 • Allmin Susaiyah, Abhinay Pandya, Aki Härmä
We present a novel method for mining opinions from text collections using generative language models trained on data collected from different populations.
no code implementations • 24 Jul 2023 • Allmin Susaiyah, Aki Härmä, Milan Petković
In natural language generation (NLG), insight mining is seen as a data-to-text task, where data is mined for interesting patterns and verbalised into 'insight' statements.
no code implementations • 19 May 2023 • Aki Härmä, Ulf Grossekathöfer, Okke Ouweltjes, Venkata Srikanth Nallanthighal
Virtual Respiratory Belt, VRB, algorithms estimate the belt sensor waveform from speech audio.
no code implementations • 20 Apr 2023 • Vadim Liventsev, Anastasiia Grishina, Aki Härmä, Leon Moonen
Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome": they tend to generate programs that semantically resemble the correct answer (as measured by text similarity metrics or human evaluation), but achieve a low or even zero accuracy as measured by unit tests due to small imperfections, such as the wrong input or output format.
no code implementations • 22 Jun 2021 • Ronja Möller, Antonino Furnari, Sebastiano Battiato, Aki Härmä, Giovanni Maria Farinella
This paper is concerned with the navigation aspect of a socially-compliant robot and provides a survey of existing solutions for the relevant areas of research as well as an outlook on possible future directions.
2 code implementations • 8 Feb 2021 • Vadim Liventsev, Aki Härmä, Milan Petković
Automatic programming, the task of generating computer programs compliant with a specification without a human developer, is usually tackled either via genetic programming methods based on mutation and recombination of programs, or via neural language models.
1 code implementation • 23 Jan 2021 • Vadim Liventsev, Aki Härmä, Milan Petković
Most state of the art decision systems based on Reinforcement Learning (RL) are data-driven black-box neural models, where it is often difficult to incorporate expert knowledge into the models or let experts review and validate the learned decision mechanisms.