Gene expression arrays are used to assess expression of exons and genes of orga- nisms. The design of expression arrays is based on a genome of laboratory strains of model organisms. The most frequent summarization algorithms used to pro- cess data from measurements are gcRMA, PLER and IterPLIER. When using expression arrays to research free living species, the measured values are influen- ced by differences in genomes of free living and model organisms. We propose a method to improve the results by removing parts of genomes influenced by known differences between species from the summarization. Removing influenced parts can improve summarization, especially on exon level. 1

Financial reports include a lot of useful information for investors, but extracting this information is time-consuming. We think text summarization is a feasible method. In this thesis, we implement BERTSUM, a state-of-the-art language model for text summarization, and evaluate the results by ROUGE metrics. The experiment was carried out on a novel and large-scale financial dataset called EDGAR-CORPUS. The BERTSUM with a transformer achieves the best performance with a ROUGE-L F1 score of 9.26%. We also hand-picked some model-generated summaries that contained common errors and investigated the causes. The results were then compared to previous research. The ROUGE-L F1 value in the previous study was much higher than ours, we think this is due to the length of the financial reports.

Polestar has during the last couple of months more than doubled its amount of customer feedback, and the forecast for the future is that this amount will increase even more. Manually reading this feedback is expensive and time-consuming, and for this reason there's a need to automatically analyse the customer feedback. The company wants to understand the customer and extract trends and topics that concerns the consumer in order to improve the customer experience. Over the last couple of years as Natural Language Processing developed immensely, new state of the art language models have pushed the boundaries in all type of benchmark tasks. In this thesis have three different extractive summarization models and three different keyword extraction methods been tested and evaluated based on two different quantitative measures and human evaluation to extract information from text. This master thesis has shown that extractive summarization models with a Transformer-based text representation are best at capturing the context in a text. Based on the quantitative results and the company's needs, Textrank with a Transformer-based embedding was chosen as the final extractive summarization model. For Keywords extraction was the best overall model YAKE!, based on the quantitative measure and human validation

El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado. / In peruvian sign language (PSL), recognition of static gestures has been proposed earlier. However, to state a conversation using sign language, it is also necessary to employ dynamic gestures. We propose a method to extract a feature vector for dynamic gestures of PSL. We collect a dataset with 288 video sequences of words related to dynamic gestures and we state a workflow to process the keypoints of the hands, obtaining a feature vector for each video sequence with the support of a video summarization technique. We employ 9 neural networks to test the method, achieving an average accuracy ranging from 80% and 90%, using 10 fold cross-validation.

In this thesis we present a novel algorithm for summarization of loops with multiple branches operating over integers. The algorithm is based on anal- ysis of a so-called state diagram, which reflects feasibility of various branch interleavings. Summarization can be used to replace loops with equivalent non-iterative statements. This supports examination of reachability and can be used for software verification. For instance, summarization may also be used for (compiler) optimizations. 1

The Internet has revolutionized the way users share and acquire knowledge. As important and popular Web-based applications, online discussion forums provide interactive platforms for users to exchange information and report problems. With the rapid growth of social networks and an ever increasing number of Internet users, online forums have accumulated a huge amount of valuable user-generated data and have accordingly become a major information source for business intelligence. This study focuses specifically on product defects, which are one of the central concerns of manufacturing companies and service providers, and proposes a machine learning method to automatically detect product defects in the context of online forums. To complement the detection of product defects , we also present a product feature extraction method to summarize defect threads and a thread ranking method to search for troubleshooting solutions. To this end, we collected different data sets to test these methods experimentally and the results of the tests show that our methods are very promising: in fact, in most cases, they outperformed the current state-of-the-art methods. / Ph. D.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第18613号 / 情博第537号 / 新制||情||95(附属図書館) / 31513 / 京都大学大学院情報学研究科知能情報学専攻 / (主査)教授 山本 章博, 教授 黒橋 禎夫, 教授 阿久津 達也 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

Football fans do not have the time to watch every game in its entirety and need an effective solution that summarizes them the story of the game. Human-generated summaries are often too short, requiring time and resources to create. We utilize the advantages of Interactive TV to create an automatic football summarization service that is cohesive, provides context, covers the necessary plays, and is concise. First, we construct a degree of interest function that ranks each play based on detailed, play-by-play game events as well as viewing statistics collected from an interactive viewing environment. This allows us to select the plays that are important to the game as well as those that are interesting to the viewer. Second, we create a visual transition that shows the progress of the ball whenever plays are skipped, allowing the viewer to understand the context of each play within the summary. Third, we enable interactive controls that allow viewers to manipulate the summary and delve deeper into the actual game whenever they wish. We validate our solution through two user studies—one to ensure that our degree of interest function selects the plays that are most interesting to the viewer, and the other to show that our transitions and interactive controls provide a better understanding of the game. We conclude that our summary solution is effective at conveying the story of a football game.

The purpose of this action research project was to determine how my practice of using graphic organizers during instruction influenced my students' ability to summarize and comprehend significant fifth grade Earth Science content regarding the Earth's changing surface. A secondary purpose was to determine the students' perceptions of how concept mapping assisted in making connections to understand the fifth grade Earth Science content regarding the Earth's changing surface. The three processes used to collect data for this research were concept maps, focus groups and the pre- and post-test results. The themes that emerged were the ability to describe, categorize and classify details, the increased accuracy of the use of vocabulary and the memory of the concepts that students' ability to recall information and understand the Earth Science concepts as evidenced through summarization and comprehension through the pre- and post-test.

Social media is a significant factor in information distribution today, and this information landscape contains a lot of different posts that compete for the user’s attention. Different factors can help catch the interest of the user, and one of them is the headline of the message. The headline can be more or less eye-catching, which can make the reader more or less interested in interacting with the post. The theme of this study is the automatized creation of eye-catching headlines that stay truthful to the content of the articles using Automatic Text Summarization. The exact method used consisted of fine-tuning the BART model, which is an existing model for Text Summarization. Other papers have been written using different models to solve this problem with more or less success, however, none have used this method. It was deemed an interesting method as it is less time- and energy-consuming than creating and training a new model entirely from scratch and therefore could be easily replicated if the results were positive. The BartForConditionalGeneration model implemented by the HuggingFace library was fine-tuned, using the Popular News Articles by Web.io. This method showed positive results. The resulting headlines were deemed faithful to the original ones, with a ROUGE-2 recall score of 0.541. They were comparably eye-catching to the human-written headlines, with the human respondents ranking them almost the same, with an average rank of 1.692 for the human-written headlines, and 1.821 for fine-tuned BART, and also getting an average score of 3.31 on a 1 to 5 attractiveness score scale. They were also deemed very comprehensible, with an average score of 0.95 on a scale from 0 to 1. / Sociala medier är idag en viktig faktor i distributionen av information. Detta nya landskap innehåller många olika inlägg som tävlar om användarens uppmärksamhet. Olika faktorer kan hjälpa till att fånga användarens blick till specifika inlägg eller artiklar, och en av dessa faktorer är rubriken. Rubriken kan vara mer eller mindre fängslande, och göra läsaren mer eller mindre intresserad av att interagera med inlägget. Temat för denna studie är att automatiskt skapa iögonfallande och intressanta rubriker, som beskriver innehå llet i artiklarna på ett korrekt sätt. Den valda metoden är automatisk textsamman fattning, och mer specifikt finjusterades BART-modellen, som är en existerande modell för textsammanfattning. Andra metoder har använts tidigare för att lösa denna problematik med mer eller mindre framgång, men ingen studie hade använt den här. Den ansågs vara intressant eftersom den är mindre tids- och energikrävande än vad det skulle vara att skapa en ny modell från grunden, och därför skulle den lätt kunna replikeras om resultatet var positivt. BartForConditionalGeneration-modellen implementerad av HuggingFace-bib lioteket finjusterades därför med hjälp av artiklar och rubriker från datasetet ’Popular News Articles’ av Web.io. Metoden visade positiva resultat. De resulterande rubrikerna ansågs trogna de ursprungliga, med en ROUGE-2 recall score på 0,541. De var jämförbart iögonfallande gentemot de mänskligt skrivna rubrikerna, då respondenterna rankade dem nästan likadant, med en genomsnittlig rankning på 1,692 för de mänskligt skrivna rubrikerna och 1,821 för rubrikerna som finjusterade BART genererade. De fick också ett genomsnittligt betyg av 3,31 på en poängskala från 1 till 5. De ansågs dessutom vara mycket lättbegripliga, med ett medelpoäng på 0,95 på en skala från 0 till 1.