Search Results for author: Aki Härmä

Found 8 papers, 2 papers with code

Opinion Mining Using Population-tuned Generative Language Models

no code implementations24 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.

Opinion Mining

Schema-Driven Actionable Insight Generation and Smart Recommendation

no code implementations24 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.

Text Generation

Fully Autonomous Programming with Large Language Models

no code implementations20 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.

Program Repair text similarity

A Survey on Human-aware Robot Navigation

no code implementations22 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.

Human Activity Recognition Robot Navigation

Neurogenetic Programming Framework for Explainable Reinforcement Learning

2 code implementations8 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.

OpenAI Gym reinforcement-learning +1

BF++: a language for general-purpose program synthesis

1 code implementation23 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.

Decision Making OpenAI Gym +2

Cannot find the paper you are looking for? You can Submit a new open access paper.