Denna studie undersökte hur automatiskt textförenkling upplevs av och hjälper högstadieelever med dyslexi. Deltagarna har fått läsa totalt fyra texter om olika ämnen uppdelat på två tillfällen där ena texten alltid varit förenklad och den andra en originaltext.Efter att läst texterna har deltagarna fått svara på läsförståelsefrågor för att se hur mycketde förstod av texten och sedan delta i en semi-strukturerad intervju för att ta reda på deras upplevelse av texten de hade läst. Resultatet från läsförståelsen delades sedan upp i degrupper som läst samma version av texterna och svaren i de semi-strukturerade intervjuerna analyserades i en tematisk analys. Resultatet visade att ingen större skillnad uppstodmellan texterna utan att båda texterna fungerade lika bra.

Fill-in-the-blank multiple choice questions (MCQs) play an important role in the educational field, but the manual generation of them is quite resource-consuming, so it has gradually turned into an attractive NLP task. Thereinto, question creation itself has become a mainstream NLP research topic, while distractor (wrong alternative) generation (DG) still remains out of the spotlight. Although several studies on distractor generation have been conducted in recent years, there is little previous work on languages other than English. The goal of this thesis is to generate multilingual distractors in Chinese, Arabic, German, and English across domains. The initial step is to construct small-sized multilingual scientific datasets (En, Zh, Ar, and De) and general datasets (Zh and Ar) from scratch. Considering that there are limited multilingual labelled datasets, unsupervised experiments based on WordNet, Word Embedding, transformer-based models, translation methods, and domain adaptation are conducted to generate their corresponding candidate distractors. Finally, the performance of methods is evaluated against our newly-created datasets, where three metrics are applied. Lastly, statistical results show that monolingual transformer-based together with translation-based methods outperform the rest of the approaches for multilingual datasets, except for German, which reaches its highest score only through the translation-based means, and distractor generation in English datasets is the simplest to implement, whereas it is the most difficult in Arabic datasets.

This research is concerned with the identification of sentiment in multimodal content. This is of particular interest given the increasing presence of subjective multimodal content on the web and other sources, which contains a rich and vast source of people's opinions, feelings, and experiences. Despite the need for tools that can identify opinions in the presence of diverse modalities, most of current methods for sentiment analysis are designed for textual data only, and few attempts have been made to address this problem. The dissertation investigates techniques for augmenting linguistic representations with acoustic, visual, and physiological features. The potential benefits of using these modalities include linguistic disambiguation, visual grounding, and the integration of information about people's internal states. The main goal of this work is to build computational resources and tools that allow sentiment analysis to be applied to multimodal data. This thesis makes three important contributions. First, it shows that modalities such as audio, video, and physiological data can be successfully used to improve existing linguistic representations for sentiment analysis. We present a method that integrates linguistic features with features extracted from these modalities. Features are derived from verbal statements, audiovisual recordings, thermal recordings, and physiological sensors signals. The resulting multimodal sentiment analysis system is shown to significantly outperform the use of language alone. Using this system, we were able to predict the sentiment expressed in video reviews and also the sentiment experienced by viewers while exposed to emotionally loaded content. Second, the thesis provides evidence of the portability of the developed strategies to other affect recognition problems. We provided support for this by studying the deception detection problem. Third, this thesis contributes several multimodal datasets that will enable further research in sentiment and deception detection.

A lot of interaction between humans take place on social media. Groups and communities are sometimes formed both with and without intention. These interactions generate a large quantity of text data. This project aims to detect dissimilarity in discourse between communities on social media using a distributed approach. A data set of tweets was used to test and evaluate the method. Tweets produced from two communities were extracted from the data set. Two Natural Language Processing techniques were used to vectorise the tweets for each community. Namely LIWC, dictionary based on knowledge acquired from professionals in linguistics and psychology, and BERT, an embedding model which uses machine learning to present words and sentences as a vector of decimal numbers. These vectors were then used as representations of the text to measure the similarity of discourse between the communities. Both distance and similarity were measured. It was concluded that none of the combinations of measure or vectorisation method that was tried could detect a dissimilarity in discourse on social media for the sample data set.

No description available.

Text clustering divides a set of texts into groups, so that texts within each group are similar in content. It may be used to uncover the structure and content of unknown text sets as well as to give new perspectives on known ones. The contributions of this thesis are an investigation of text representation for Swedish and an evaluation method that uses two or more manual categorizations. Text clustering, at least such as it is treated here, is performed using the vector space model, which is commonly used in information retrieval. This model represents texts by the words that appear in them and considers texts similar in content if they share many words. Languages differ in what is considered a word. We have investigated the impact of some of the characteristics of Swedish on text clustering. Since Swedish has more morphological variation than for instance English we have used a stemmer to strip suffixes. This gives moderate improvements and reduces the number of words in the representation. Swedish has a rich production of solid compounds. Most of the constituents of these are used on their own as words and in several different compounds. In fact, Swedish solid compounds often correspond to phrases or open compounds in other languages.In the ordinary vector space model the constituents of compounds are not accounted for when calculating the similarity between texts. To use them we have employed a spell checking program to split compounds. The results clearly show that this is beneficial. The vector space model does not regard word order. We have tried to extend it with nominal phrases in different ways. Noneof our experiments have shown any improvement over using the ordinary model. Evaluation of text clustering results is very hard. What is a good partition of a text set is inherently subjective. Automatic evaluation methods are either intrinsic or extrinsic. Internal quality measures use the representation in some manner. Therefore they are not suitable for comparisons of different representations. External quality measures compare a clustering with a (manual) categorization of the same text set. The theoretical best possible value for a measure is known, but it is not obvious what a good value is -- text sets differ in difficulty to cluster and categorizations are more or less adapted to a particular text set. We describe an evaluation method for cases where a text set has more than one categorization. In such cases the result of a clustering can be compared with the result for one of the categorizations, which we assume is a good partition. We also describe the kappa coefficient as a clustering quality measure in the same setting. / Textklustring delar upp en mängd texter i grupper, så att texterna inom dessa liknar varandra till innehåll. Man kan använda textklustring för att uppdaga strukturer och innehåll i okända textmängder och för att få nya perspektiv på redan kända. Bidragen i denna avhandling är en undersökning av textrepresentationer för svenska texter och en utvärderingsmetod som använder sig av två eller fler manuella kategoriseringar. Textklustring, åtminstonde som det beskrivs här, utnyttjar sig av den vektorrumsmodell, som används allmänt inom området. I denna modell representeras texter med orden som förekommer i dem och texter som har många gemensamma ord betraktas som lika till innehåll. Vad som betraktas som ett ord skiljer sig mellan språk. Vi har undersökt inverkan av några av svenskans egenskaper på textklustring. Eftersom svenska har större morfologisk variation än till exempel engelska har vi tagit bort suffix med hjälp av en stemmer. Detta ger lite bättre resultat och minskar antalet ord i representationen. I svenska används och skapas hela tiden fasta sammansättningar. De flesta delar av sammansättningar används som ord på egen hand och i många olika sammansättningar. Fasta sammansättningar i svenska språket motsvarar ofta fraser och öppna sammansättningar i andra språk. Delarna i sammansättningar används inte vid likhetsberäkningen i vektorrumsmodellen. För att utnyttja dem har vi använt ett rättstavningsprogram för att dela upp sammansättningar. Resultaten visar tydligt att detta är fördelaktigt I vektorrumsmodellen tas ingen hänsyn till ordens inbördes ordning. Vi har försökt utvidga modellen med nominalfraser på olika sätt. Inga av våra experiment visar på någon förbättring jämfört med den vanliga enkla modellen. Det är mycket svårt att utvärdera textklustringsresultat. Det ligger i sakens natur att vad som är en bra uppdelning av en mängd texter är subjektivt. Automatiska utvärderingsmetoder är antingen interna eller externa. Interna kvalitetsmått utnyttjar representationen på något sätt. Därför är de inte lämpliga att använda vid jämförelser av olika representationer. Externa kvalitetsmått jämför en klustring med en (manuell) kategorisering av samma mängd texter. Det teoretiska bästa värdet för måtten är kända, men vad som är ett bra värde är inte uppenbart -- mängder av texter skiljer sig åt i svårighet att klustra och kategoriseringar är mer eller mindre lämpliga för en speciell mängd texter. Vi beskriver en utvärderingsmetod som kan användas då en mängd texter har mer än en kategorisering. I sådana fall kan resultatet för en klustring jämföras med resultatet för en av kategoriseringarna, som vi antar är en bra uppdelning. Vi beskriver också kappakoefficienten som ett kvalitetsmått för klustring under samma förutsättningar. / QC 20101220

<p>  </p> <p>This study addresses a critical gap in the existing literature by investigating the manifestation of impoliteness through the use of emojis within the online Vietnamese community on social media. The research is guided by three central questions: (1) How do Vietnamese Facebook users use emojis in their posts and comments? (2) How do Vietnamese Facebook users perceive impolite behaviors in cyberspace? and (3). What strategies do Vietnamese speakers employ to express impoliteness with emojis on social media? Quantitative and qualitative analyses were performed on a corpus of posts and comments on a Facebook showbiz confession page. Results show that facial emojis, particularly those forming homogeneous sequences, are preferred, with laughter-related emojis prominently featured. Additionally, emotive particles, together with expletives, frequently co-occur with emojis, compensating for absent extralinguistic cues in computer-mediated communication. By administering checks using dictionaries, mutual information scores, collocation visualizations, and cosine similarity, a nuanced understanding of impoliteness in CMC was achieved. Religious influences, particularly from Buddhism, were found to play a significant role in shaping Vietnamese impoliteness perception, exemplified by terms such as <em>vô duyên</em> and <em>sân si</em>. A coding scheme informed by findings from the second research question on a sample of 100 first posts and comments in the main corpus was used. The study further substantiates the hypothesis that Vietnamese speakers predominantly employ implicational impoliteness strategies, particularly through multimodal mismatches facilitated by emojis. Conventionalized formulas featuring emojis were infrequent, suggesting a preference for more dynamic and context-specific impoliteness expressions. This research contributes to the refinement of impoliteness theoretical and methodological approaches, as well as providing a foundation for further studies in online discourse and natural language processing. </p>

Troubleshooting radio devices that power modern mobile networks is currently a manual and labour-intensive process, where speed is crucial to minimize network downtime. Therefore, there is a strong interest in building a retrieval system capable of intelligent search and retrieval in radio logs. To facilitate effective retrieval, several retrievers were evaluated using different configurations. First, a RoBERTa language model was further pretrained on a dataset of unannotated radio logs. Then, a proprietary annotated retrieval dataset named the Event LogRetrieval (ELR) dataset was collected and utilized along with the MS MARCOretrieval dataset for training and evaluating the retrieval models. The evaluation compared different retrieval paradigms for log retrieval; evaluated the impact of further pretraining the language model on log data; and investigated which con-figuration yielded the best performance. The results of the investigation show that the late interaction retrieval paradigm used by the ColBERT model performs best for log retrieval. The results also showed that while further pretraining the language model on logs did improve the representations of log data, it did not improve the performance of the implemented retriever. The investigation into the retrieval datasets showed that fine-tuning on the small ELR dataset is insufficient and that fine-tuning on the larger MS MARCO dataset yielded better performance. The best performance was seen though when first fine-tuning on MSMARCO and then on ELR.

In this thesis, we work towards bridging the gap between two distinct areas: noisy text handling and text summarisation. The overall goal of the paper is to examine the effects of noise in the training of convolutional neural networks for text summarisation, with a view to understanding how to effectively create a noise-robust text-summarisation system. We look specifically at the problem of abstractive text summarisation of noisy data in the context of summarising error-containing documents from automatic speech recognition (ASR) output. We experiment with adding varying levels of noise (errors) to the 4 million-article Gigaword corpus and training an encoder-decoder CNN on it with the aim of producing a noise-robust text summarisation system. A total of six text summarisation models are trained, each with a different level of noise. We discover that the models with a high level of noise are indeed able to aptly summarise noisy data into clean summaries, despite a tendency for all models to overfit to the level of noise on which they were trained. Directions are given for future steps in order to create an even more noise-robust and flexible text summarisation system.

In this thesis, I investigate a decades-old problem found in the stop system of Proto-Indo-European (PIE). More specifically, I will be investigating the paucity of */b/ in the forms reconstructed for the ancient, hypothetical language. As cross-linguistic evidence and phonological theory alone have fallen short of providing a satisfactory answer, herein will I employ modern empirical methods of linguistic investigation, namely laboratory phonology experiments and computational database analysis. Following Byrd 2015, I advocate for an examination of synchronic phenomena and behavior as a method for investigating diachronic change. In Chapter 1, I present an overview of the various proposed phonological systems of PIE and some of the explanations previously given for the enigmatic rarity of PIE */b/. Chapter 2 presents a detailed account of three lab phonology experiments I conducted in order to investigate perceptual confusability as a motivator of asymmetric merger within a system of stop consonants. Chapter 3 presents the preliminary form and findings of a computational database of reconstructed forms in PIE that I created and have named the Database of Etymological Reconstructions Beginnning in Proto-Indo-European (DERBiPIE). The final chapter, Chapter 4, offers a summary of the work presented herein and conclusions that may be drawn, offering suggestions for continued work on the topic and others like it.