|
|
Automatization of Generating Product Descriptions With Neural Language Models
Hrouda, Václav ; Kasner, Zdeněk (advisor) ; Helcl, Jindřich (referee)
Product descriptions are an important part of product presentation in e-commerce. This bachelor thesis explores the possibilities of using language models based on the Transformer architecture to generate product descrip- tions based on textual product information. Data from a real ecommerce store was used and three different approaches were tested during the work. Fine-tuning of the GPT2 small Czech model, using the Mistral model with the translation of its inputs and outputs into English and directly using Chat- GPT on the Czech data. A combination of automated metrics and human moderation was used to evaluate the generated texts. The result is a clear ranking of these approaches (ChatGPT, Mistral, GPT2 small Czech), with none proving sufficiently reliable for practical use.
|
|
|
Object layout in a 2D room based on text description
Pavelka, Jan ; Rosa, Rudolf (advisor) ; Kasner, Zdeněk (referee)
This thesis presents a solution for generating structured description a 2D map of a room from a bird's eye view based on textual description in Czech. It focuses on identifying physical objects and their mutual relative positions in the description. It describes linguistic phenomena of the information extraction and their usage in the im- plementation. It shows how syntactic parsing can be used for this task. Then, it uses a genetic algorithm to find a feasible layout of the extracted objects with respect to spatial constraints constructed from the extracted information. 1
|
|
|
Methods of User-Assisted Summarization of Meetings
Kmječ, František ; Bojar, Ondřej (advisor) ; Kasner, Zdeněk (referee)
Automated minuting, or meeting summarization, is the task of accurately capturing the contents of a meeting in a short text or in bullet points. Recently, a lot of progress has happened in this area, largely due to the rise of the large language models. However, most fully automated approaches have severe limitations; either their outputs are vague or they are prone to hallucinations. We explore the possibility of user-assisted minuting to provide factual accuracy as well as coverage. We introduce a novel open-source tool, Minuteman, integrated with JitSi Meet to explore the methods by which users can interact with summarization models. We then analyze data gathered from multiple experiments with users and show how similar means of interaction can be of use in increasing summary quality. 1
|
|
|
Generation of tennis singles results
Prokop, Dominik ; Rosa, Rudolf (advisor) ; Kasner, Zdeněk (referee)
This thesis deals with the problem of generating short articles about past tennis singles from structured data. Articles are generated by using templates heuristically obtained from the original news articles. The result of this thesis is a template database and a graphic application which using these templates for given input generates corresponding short articles. This thesis also includes evaluation of the application outputs which shows that 64 % of the generated texts are correct. 1
|
|
|
Generating text from structured data
Trebuňa, František ; Rosa, Rudolf (advisor) ; Kasner, Zdeněk (referee)
In this thesis we examine ways of conditionally generating document-scale natural language text given structured input data. Specifically we train Deep Neural Network models on RotoWire dataset containing statistical data about basketball matches paired with descriptive summaries. First, we analyse the dataset and propose several prepro- cessing methods (e.g. Byte Pair Encoding). Next, we train a baseline model based on the Encoder-Decoder architecture on the preprocessed dataset. We discuss several prob- lems of the baseline and explore advanced Deep Neural Network architectures that aim to solve them (Copy attention, Content Selection, Content Planning). We hypothesize that our models are not able to learn the structure of the input data and we propose a method reducing its complexity. Our best model trained on the simplified data manages to outperform the baseline by more than 5 BLEU points. 1
|
guest ::
