Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Big Data Analysis and Machine Learning at Scale with Oracle Cloud Infrastructure
Published in CERN Openlab Zenodo, 2019
This work has successfully deployed two different use cases of interest for High Energy Physics using cloud resources.
Download here
Cooking recipes generator utilizing a deep learning-based language model
Published in PUT Poznań Bachelor Thesis, 2020
Cooking recipes generator utilizing a deep learning-based language model
Download here
RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation
Published in INLG, 2020
Semi-structured text generation is a non-trivial problem. Although last years have brought lots of improvements in natural language generation, thanks to the development of neural models trained on large scale datasets, these approaches still struggle with producing structured, context- and commonsense-aware texts. Moreover, it is not clear how to evaluate the quality of generated texts. To address these problems, we introduce RecipeNLG – a novel dataset of cooking recipes. We discuss the data collection process and the relation between the semi-structured texts and cooking recipes. We use the dataset to approach the problem of generating recipes. Finally, we make use of multiple metrics to evaluate the generated recipes.
Download here
On the Context-Free Ambiguity of Emoji
Published in ICWSM, 2022
Emojis come with prepacked semantics making them great candidates to create new forms of more accessible communications. Yet, little is known about how much of this emojis semantic is agreed upon by humans, outside of textual contexts. Thus, we collected a crowdsourced dataset of one-word emoji descriptions for 1,289 emojis presented to participants with no surrounding text. The emojis and their interpretations were then examined for ambiguity. We find that with 30 annotations per emoji, 16 emojis (1.2%) are completely unambiguous, whereas 55 emojis (4.3%) are so ambiguous that their descriptions are indistinguishable from randomly chosen descriptions. Most of studied emojis are spread out between the two extremes. Furthermore, investigating the ambiguity of different types of emojis, we find that an important factor is the extent to which an emoji has an embedded symbolical meaning drawn from an established code-book of symbols. We conclude by discussing design implications.
Download here
talks
Big Data Analysis and Machine Learning in the Cloud
Published:
The final pitch talk of CERN Openlab Summer Student Programme 2019, where I presented my project results. The recording is available on CERN Document Server.
AI at CERN
Published:
In 2019, together with Bartłomiej Borzyszkowski, we had opportunity to present our research at ML in PL - the biggest conference in Poland devoted to artificial intelligence. The recording is available on youtube
RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation
Published:
The poster session talk which accompanied the RecipeNLG paper we published on INLG2020. The session recording is available on Panopto