Skip to main content
Login | Suomeksi | På svenska | In English

Browsing by master's degree program "Kielellisen diversiteetin ja digitaalisten ihmistieteiden maisteriohjelma"

Sort by: Order: Results:

  • Vaija, Panu (2023)
    Depressive disorders and especially Major Depressive Disorder (MDD) have recently raised a lot of concerns. According to Bains & Abdijadid, (2022), in 2030 MDD will be the most common concern in terms of mental well-being and Kessler & Bromet (2013) pointed out that MDD “has one of the highest lifetime prevalence among psychiatric disorders”, and for this reason MDD results in a significant burden from an individual and societal perspective (Lépine & Briley, 2011). Anhedonia which is a core symptom of MDD (Gorwood 2008, Liang et al. 2022) can be defined as the “inability to enjoy experiences or activities that normally would be pleasurable” (APA Dictionary of Psychology, n.d.-c). Its effects on cognitive processes such as reward responsiveness has been the interest of various studies. Pizzagalli et al. (2008) demonstrated in their study that individuals suffering from MDD and experiencing anhedonic symptoms have a blunted reward responsiveness compared to some healthy subjects. This master thesis aimed to replicate Pizzagalli et al. (2008) study to reinvestigate anhedonia´s impact on reward responsiveness as well as anxiety´s role since individuals suffering from MDD also face anxiety or anxiety disorder (Xin et al. 2015).Two groups were formed, a clinical group (N=29) based on the DSM-IV criteria and a control group (N=20), and both groups were given the Face Game or the Probabilistic Reward Task (Pizzagalli et al. 2008) to measure reward responsiveness. Reward responsiveness was computed as “response bias” and the perceived difficulty of the task as “discriminability”. The results showed no significant difference in response bias scores between the depressed and healthy participants, and no significant correlations were found between depression scores, anhedonia scores, anxiety scores, and response bias scores. An effect of the experimental task’s blocks on response bias and discriminability scores was found, but no interaction effect (group * block) was found for the response bias and discriminability scores. Thus, we cannot argue in favor of the results obtained by Pizzagalli et al, (2008) that individuals suffering from MDD and especially experiencing anhedonic symptoms are more likely to have a blunted reward sensitivity compared to some healthy subjects. The statistically non-significant results were attributed to the small sample size, the complexity of the task and its design. Therefore, further investigations should focus on getting larger clinical and control groups and they also should redefine some aspects of the experimental task to make it more sensitive to any changes to reward responsiveness among individuals suffering from MDD and experiencing anhedonic symptoms.
  • Männistö, Johanna (2024)
    Large Language Models (LLMs) demonstrate increasingly impressive capabilities as they grow in size, but these ever-growing models come at the expense of high training, inference, storage, and deployment costs. Parameter Efficient Fine-Tuning (PEFT) methods have emerged as a response to the growing cost of performance and have demonstrated success when used with general language models. PEFT methods have also been applied to train models with fewer than one billion parameters on code tasks such as code summarization. However, few have compared multiple PEFT approaches when training models on code generation tasks. We investigate the training methods' impact on model performance on code generation tasks by training five model families, ranging from 124 million to 15.5 billion parameters, using four PEFT approaches and regular fine-tuning. We find the impact of each PEFT method varies depending on model size and dataset size and quality. Larger models required fewer updated parameters and saw the best performance with prompt-tuning and LoRA approaches, while models smaller than 1.5 billion parameters saw the best results with more parameter updates, such as with full fine-tuning. In addition to differences in performance results, we also find that as model sizes, increase memory savings and training speeds become increasingly similar. Surprisingly, we see a decline in model performance after training large models. We hypothesize this is due to data misalignment between the pre-training data and sub-optimal training hyperparameters. The results of this study suggest that LoRA, when applied to all linear layers, is an effective and competitive training method for code generation tasks across various model sizes. For models with fewer than 1.5 billion parameters, if the resources are available full fine-tuning should be done for optimal performance, which is not the case for larger models. We also report all training hyperparameters to aid others in determining the best hyperparameters for their use case. Finally, this study discusses the benefits and criticisms of commonly used metrics, and their impact on evaluating model performance.
  • Törö, Tuukka (2022)
    In recent years, advances in deep learning have made it possible to develop neural speech synthesizers that not only generate near natural speech but also enable us to control its acoustic features. This means it is possible to synthesize expressive speech with different speaking styles that fit a given context. One way to achieve this control is by adding a reference encoder on the synthesizer that works as a bottleneck modeling a prosody related latent space. The aim of this study was to analyze how the latent space of a reference encoder models diverse and realistic speaking styles, and what correlation there is between the phonetic features of encoded utterances and their latent space representations. Another aim was to analyze how the synthesizer output could be controlled in terms of speaking styles. The model used in the study was a Tacotron 2 speech synthesizer with a reference encoder that was trained with read speech uttered in various styles by one female speaker. The latent space was analyzed with principal component analysis on the reference encoder outputs for all of the utterances in order to extract salient features that differentiate the styles. Basing on the assumption that there are acoustic correlates to speaking styles, a possible connection between the principal components and measured acoustic features of the encoded utterances was investigated. For the synthesizer output, two evaluations were conducted: an objective evaluation assessing acoustic features and a subjective evaluation assessing appropriateness of synthesized speech in regard to the uttered sentence. The results showed that the reference encoder modeled stylistic differences well, but the styles were complex with major internal variation within the styles. The principal component analysis disentangled the acoustic features somewhat and a statistical analysis showed a correlation between the latent space and prosodic features. The objective evaluation suggested that the synthesizer did not produce all of the acoustic features of the styles, but the subjective evaluation showed that it did enough to affect judgments of appropriateness, i.e., speech synthesized in an informal style was deemed more appropriate than formal style for informal style sentences and vice versa.
  • Salmi, Senja (2024)
    This study gives a glimpse on some elements that were used in Neo-Assyrian names. The data set used in this study is ‘A Social Network of the Prosopography of the Neo-Assyrian Empire’ that has been edited by Dr Heidi Jauhiainen and Dr Tero Alstola. The data set is based on the ‘The Prosopography of Neo-Assyria (PNA)’ project directed by Dr Simo Parpola at the University of Helsinki. The data set originally included names in more than ten different languages, but this study focuses solely on names that are in Akkadian, so names of other origins were left out. Also, only names that were identified as male were studied. As this study is a master’s thesis for digital humanities, digital methods were used. Neo-Assyrian names offer an interesting insight to the society of Neo-Assyria and how the Akkadian language was used. The names were short phrases or sentences, so they can tell a lot of the surrounding society. Especially theophoric elements and how they were connected to other elements is something that this study focuses on. Theophoric elements are usually names of deities which were often used in Neo-Assyrian and Neo-Babylonian names. The most common theophoric elements in this data set were Nabû, Aššur, and Bēl. In addition of theophoric elements, other elements were studied too. The most frequent other element was naṣāru ‘to protect’ which was almost only found together with theophoric elements. Other popular elements were nadānu ‘to give’ and šarru ‘king’. The naming patterns of Neo-Babylonia have been studied more than Neo-Assyrian practices. For example, it was quite common for Neo-Babylonians to give their first-born son a name that incorporated the elements aplu ‘heir’ and the theophoric element Marduk. In the names of second-born sons the theophoric element Nabû was often combined with some form of the verb nadānu ‘to give’. Based on this study it seems that a similar practice of naming a second-born son might have been used in Neo-Assyria as well. However, the element aplu was very infrequent in the studied data set.
  • Hotti, Helmiina (2023)
    Diagrams are a mode of communication that offers challenges for its computational processing. The challenges arise from the multimodal nature of diagrams. This means that diagrams combine several types of expressive resources to achieve their communicative purposes, such as textual elements, connective elements such as arrows and lines, and illustrations. Humans interpret diagrams by judging how these different expressive resources work together to reach the communicative goals set for the diagram. In order to do that, humans make inferences of the diagram layout and the implicit relations that exist between different parts of the diagram. In order to build computational methods for diagram understanding, large amounts of data annotated with these implicit relations is required. Traditionally, these types of discourse structure annotations have been annotated by experts, due to the difficulty of the task and the requirement that the annotator is familiar with the theoretical framework used for describing discourse relations. The chosen theory for modeling discourse relations in diagrams is Rhetorical Structure Theory, originally developed for modeling textual coherence but applicable to multimodal data as well. This thesis explores the possibility to gather discourse relation annotations for multimodal diagram data with crowdsourcing; employing naive workers on crowdsourcing platforms to complete annotation tasks for a monetary reward. Adapting the task of discourse relation annotation to be feasible for naive workers has been proven challenging by past research concerned with only textual data, and the multimodality of the data adds to the complexity of the task. This thesis presents a novel method for gathering multimodal discourse relation annotations using crowdsourcing and methods of natural language processing. Two approaches are explored: adopting an insertive annotation task where the workers are asked to describe the relationship between two diagram elements in their own words and adopting a multiple-choice task, converting the formal definitions of Rhetorical Structure Theory to understandable phrases to annotate with. Natural language processing is used in the first approach to validate the language and structure of the crowdsourced descriptions. The results of the first approach highlight the difficulty of the task: the workers show tendencies of relying heavily on example descriptions shown in the task instructions and difficulty of grasping the differences of the more fine-grained relations. The multiple-choice approach seems more promising, with annotation agreement with expert annotators higher than in previous research concerned with discourse relations in textual data. The manual inspection of the annotated diagrams show that the disagreement of the crowdworkers and expert annotators is often justifiable; both annotations represent a valid interpretation of the discourse relation. This highlights one of the main challenges of the task, which is the ambiguity of some of the relations. Future work is encouraged to consider this by adopting an approach that is less concerned with a pre-defined set of relations and more interested in how the different discourse relations are actually perceived.
  • Wikström, Alexandra (2022)
    Ihmiset muuttavat äänentuotantoaan kuuluvammaksi meluisassa ympäristössä refleksinomaisesti. Tätä ilmiötä kutsutaan Lombard-efektiksi. Efekti saa puhujan tuottamaan Lombard-puhetta, jota on tutkittu jo yli vuosisadan ajan eri näkökulmista. Lombard-puheen akustiikalle ominaista ovat korotettu äänenpainetaso, korotettu puheäänen perustaajuus, muutokset äänen osataajuuksissa sekä muissa äänen spektrin rakenteissa. Lisäksi Lombard-puheessa vokaalien pituuksilla on tapana kasvaa, ja äärimmäisissä meluolosuhteissa hyperartikulaatiota voi esiintyä. Puhetilanteeseen sisältyvä kommunikatiivinen aspekti on keskeistä ilmiön synnylle. Tämän tutkielman tavoitteena oli tutkia puheentuottoa keskustelutilanteessa, jossa samanaikaisesti toinen keskustelijoista on altistettuna melulle ja tuottaa täten Lombard-puhetta, ja toinen keskustelija kommunikoi hiljaisuudessa ilman taustamelun suoria vaikutuksia, ja selvittää, onko puheen akustiikassa tai ymmärrettävyydessä eroavaisuuksia tällaisessa epäsymmetrisessä tilanteessa verrattuna symmetriseen puhetilanteeseen, jossa molempien puhujien ääniympäristö on sama. Tutkimusta varten kaksi paria suomenkielisiä keskustelijoita (yhteensä neljä osallistujaa, kaikki naisia) ratkoivat pareittain sudokupohjaisia tehtäviä kolmessa eri taustamelutilanteessa: (1) hiljaisuudessa, (2) molempien ollessa taustamelussa (symmetrinen), ja (3) vain toisen keskustelijan ollessa taustamelussa (asymmetrinen). Taustamelu, jota soitettiin koehenkilöille 75 dB äänenpainetasolla, oli laadultaan cocktail-melua, joka sisältää niin kutsuttua puheensorinaa jossa useampi puhuja puhuu päällekkäin. Keskustelut äänitettiin ja niistä kerättiin yhteensä 453 maalitavua, joista kaikista analysoitiin keskimääräinen äänenpainetaso, ja 417 maalitavusta analysoitiin keskimääräinen perustaajuus. Äänenpainetason ja perustaajuuden arvot normalisoitiin ja arvoille suoritettiin keskiarvoja ja variansseja vertailevat tilastolliset testit. Odotetusti kaikki puhujat korottivat äänenpainetasoaan ja perustaajuuttaan siirryttäessä hiljaisesta keskustelutilanteesta symmetriseen taustamelutilanteeseen, jossa molemmat keskustelukumppanit tuottivat Lombard-puhetta. Henkilöt, jotka asymmetrisessä keskustelutilanteessa olivat itse hiljaisuudessa ja kommunikoivat keskustelukumppanille, joka oli melussa, korottivat sekä äänenpainetasoaan että perustaajuuttaan asymmetrisessä keskustelutilanteessa verrattuna hiljaiseen keskustelutilanteeseen. Lisäksi toinen näistä puhujista korotti sekä äänenpainetasoaan että perustaajuuttaan lähes oman Lombard-puheensa tasolle, jota mitattiin symmetrisessä tilanteessa. Puhujat, jotka olivat altistettuna melulle asymmetrisessä tilanteessa, käyttivät keskimäärin matalampaa äänenpainetasoa asymmetrisessä kuin symmetrisessä tilanteessa, vaikka tuottivatkin Lombard-puhetta molemmissa tilanteissa. Väärin kuultuja maalitavuja ei havaittu asymmetrisessä tilanteessa, vaan henkilöt, jotka olivat kyseisessä tilanteessa hiljaisuudessa, onnistuivat korottamaan ääntään tarvittavalle tasolle, jotta ratkaiseva tieto saatiin kommunikoitua melussa olevalle henkilölle. Tämä tutkimus osoitti, että kahden keskustelukumppanin ääniympäristöjen ollessa eriävät, kumpikaan keskustelijoista ei tuota täysin sentyyppistä puhetta, joka olisi sopivaa heidän senhetkiseen ääniympäristöönsä, vaan puheentuottoon vaikuttaa myös välillisesti keskustelukumppanin ääniympäristö. Lisäksi tutkimus osoitti, että siinä missä puhetilanteen kommunikatiivisuus voi lisätä Lombard-efektin vaikutuksia, se voi myös häivyttää niitä. Jatkotutkimuksissa tulisi kerätä enemmän dataa ja suorittaa datalle laajempaa analyysiä.
  • Brenzoni, Sofia (2023)
    The present study aims at providing insights into the dynamics of language attitudes in native Italian speakers residing in Italy towards English as a foreign language. In the past decades, English has acquired an international role and has become increasingly important in many areas of life. Nonetheless, the English language proficiency of native Italians appears to fall behind, especially when compared with learners from other European countries. With this in mind, this thesis has two main objectives: 1) Identifying the overall attitudes of native Italian speakers residing in Italy with regard to English, and 2) examining whether there are any meaningful relationships between these language attitudes and specific profile characteristics, i.e., the individuals’ age, gender, region of residence, level of education, residence abroad, and self-reported English language proficiency. For this purpose, the research was carried out within the framework of the discipline of sociolinguistics and a quantitative study was conducted by employing a direct measure strategy. The questionnaire was distributed online across Italy and gathered a total of 470 submissions. The obtained data was subsequently analysed using methods of descriptive statistics and correlation tests. The participants’ answers to the open-ended questions were used as supporting information to the quantitative data. The results of the study revealed that Italian individuals residing in Italy have a mostly favourable orientation towards English as a foreign language. Individuals significantly value the importance of possessing good English language skills nowadays while at the same time showing a sound sense of Italian group identity. The research reports a clear perception of the different roles that Italian and English play within the Italian society. Attitudes to English are mostly favourable regardless of age and, while gender differences are not too strongly marked, women display more positive attitudes towards the language. The research also revealed that individuals who have achieved a higher level of education are more prone to view English in a positive light. The findings showed that the attitudes and opinions towards English as a foreign language among Italians are mostly favourable regardless of the individuals’ regions of residence. Moreover, having had past experiences abroad does not significantly influence the way that individuals perceive English as a foreign language. Finally, individuals who perceive their English language skills to be high also tend to have more favourable attitudes towards it.
  • Vehomäki, Varpu (2022)
    Social media provides huge amounts of potential data for natural language processing but using this data may be challenging. Finnish social media text differs greatly from standard Finnish and models trained on standard data may not be able to adequately handle the differences. Text normalization is the process of processing non-standard language into its standardized form. It provides a way to both process non-standard data with standard natural language processing tools and to get more data for training new tools for different tasks. In this thesis I experiment with bidirectional recurrent neural network models and models based on the ByT5 foundation model, as well as the Murre normalizer to see if existing tools are suitable for normalizing Finnish social media text. I manually normalize a small set of data from the Ylilauta and Suomi24 corpora to use as a test set. For training the models I use the Samples of Spoken Finnish corpus and Wikipedia data with added synthetic noise. The results of this thesis show that there are no existing tools suitable for normalizing Finnish written on social media. There is a lack of suitable data for training models for this task. The ByT5-based models perform better than the BRNN models.
  • Torvinen, Niina (2024)
    Previous research has found connections between Frontal Alpha Asymmetry (FAA) and different personality traits, psychological disorders, and stress. FAA has also been found to differ between people scoring higher on Behavioral Inhibition scale (BIS) or Behavioral Activation scale (BAS). Yet, there are incongruous results on whether the FAA can be found from the resting or the active state brain activity. Additionally, research on musical expertise and its connections to the BIS/BAS scores and frontal alpha power is scarce, although studies report that musicians tend to score higher on openness, compared to non-musicians, and their brain activity differs from non-musicians. The aim of this thesis was to study possible interactions between FAA, BIS/BAS scores and musical expertise. The EEG data were collected from musicians (N = 20) and non-musicians (N = 21) while they were engaged in two sound discrimination tasks. Additionally, participants were asked to rate their performance, emotions, and arousal. Participants were divided into two groups according to their BAS scores, and the results of the questionnaires and frontal alpha power were compared between musicians and non-musicians, and between two BAS-groups. The results did not show significant interaction between BAS-scores and questionnaire scores or musical expertise and questionnaire scores. Additionally, no significant difference in FAA was found between participants scoring lower or higher on BAS-scale, or between musicians and non-musicians. Yet, musicians overall alpha power was higher than non-musicians, and most of the musicians scored higher on BAS scale, compared to non-musicians. Future studies on BIS/BAS sensitivity should take into account possible connection between musical experts and personality scores.
  • Berg, Anton (2022)
    This master's thesis seeks to conceptually replicate psychologist Michael Kosinski's study, published in 2021 in Nature Scientific Reports, in which he trained a cross-validated logistic regression model to predict political orientations from facial images. Kosinski reported that his model achieved an accuracy of 72\%, which is significantly higher than the 55\% accuracy measured in humans for the same task. Kosinski's research attracted a huge amount of attention and also accusations of pseudoscience. Where Kosinski trained his model with facial features containing information for example about head position and emotions, in this thesis I use a deep learning convolutional neural network for the same task. Also, I train my model with Finnish data, consisting of photos of the faces of Finnish left- and right-wing candidates gathered from the 2021 municipal elections. I research whether a convolutional neural network can learn to predict from candidates' faces whether a member of a Finnish party belongs to either the right-wing Coalition Party (Coalition) or the left-wing Left Alliance (Left Alliance) with better than 55\% accuracy, and what is the possible role of color information on the classification accuracy of the model. On this basis, I also consider the wider ethical issues surrounding these types of models and the technological advances they bring. There has been a recent ethical debate on the widespread use of facial recognition technology in relation to issues such as human autonomy, privacy, and civil liberties. In the context of previous scientific findings, there has also been debate about the potential ability of facial recognition technologies to reveal information about our most personal traits, such as sexual orientation, personality, and emotional states. Thus, facial recognition technologies are also closely related to privacy issues. In his original article, Michael Kosinski did not underestimate the many problematic ethical issues that the use of facial recognition technology can raise. He did, however, underline the role of science in trying to determine the function, capability, and accuracy of these technologies. Only through research can we gain insights into these technologies, which can then potentially be used to inform societal decision-making. This research approach is also the aim of this Master's thesis.
  • Puzanauskaite, Migle (2023)
    The thesis explores object case-marking under long-distance negation. Opposed to local negation (where the negated verb governs the object directly), long-distance (or non-local) refers to negation where the main negated verb governs a clause, which includes an object. The aim of the thesis is to investigate how social (such as age, region of origin, education, bilingualism, second languages) and linguistic factors (structural verb types) might affect case choice between genitive and accusative in negated infinitival clauses in Lithuanian. The data was collected through a questionnaire, distributed to speakers of Lithuanian through Facebook. In total, 116 responses were received. The results were analyzed using statistical methods (Chi-square or Fisher's exact test for statistical significance, Cramer's V for strength of relationship). The findings show that age, region of origin and bilingualism show the strongest relationship with case choice. The choice of accusative is least frequent among the youngest, and most frequent among the oldest respondents. Accusative is also most common among residents of Mažoji Lietuva, followed by Vilnius, while speakers of Kaunas prefer the genitive. Russian-Lithuanian bilinguals favor accusative significantly more often that native speakers of Lithuanian, while Polish-Lithuanian bilinguals favor the genitive. Education and second languages (specifically, Russian and Polish) have weaker, but statistically significant relationships with case choice. The higher the degree of education the less frequent use of accusative, and more frequent the genitive. Second languages reflect the trends of bilingualism, but to a smaller degree: speakers of Russian as a second language use accusative more often, while speakers of Polish as a second language prefer the genitive. Case-marking variation under long-distance negation is still very much viable in Modern Lithuanian and the frequencies of each case used in object marking reflect those of earlier research. Structural verb types play a role in case choice, with some less and others more prone to take an accusative object: same-subject verbs are least likely to take an accusative object, the possibility increases with different-subject verbs and verb+noun complexes and reaches its height with dative experiencer verbs.
  • Rahman, Dean (2022)
    There are comprehensive requirements in Finland for procurement by any government organization to go through a tendering process where information about each tender is made available not only to vendors and service providers, but to everyone else in Finland as well. This is accomplished through the website Hilma and should make tenders easy to find. Moreover, in Finnish, variance in domain terminology is not thought to be the problem that it is in English. For instance, the last four years of tenders on Hilma never refer to jatkuva parantaminen as toiminnallinen erinomaisuus whereas “continuous improvement” and “operational excellence” could be used interchangeably in English. And yet, it is considered very difficult for a vendor or service provider to find applicable tenders on Hilma. Rather than lexical variability being the cause as it might be in English, the differences in concept paradigms between the private and public sectors in Finland pose the challenge. Whereas a taxi company representative would be looking for tenders about transportation services, a public officer could be posting a tender about social equity for the disabled. The second difficulty is that the Hilma search engine is purely Boolean with restrictive string match criteria rather than inviting natural language questions. Finally, the Hilma search engine does not account for Finnish being a highly inflecting and compounding language where single words usually morph instead of taking on adpositions, and where compound words are affixed together without hyphenation. Many information retrieval approaches would look outside the corpus for query expansion terms. Natural language processing might also offer the potential to look for paraphrases in existing parallel corpora on tenders throughout the European Union rather than in Hilma. However, this thesis focuses on clustering the tenders posted in Finnish on Hilma, applying the comprehensive workflow of the very recent BERTopic package for Python. All documents in each cluster are concatenated and the highest TFIDF-scoring words in the concatenated document are slated to be “search extension terms.” If one of the terms were to be entered by a Hilma user, the user would be invited to perform parallel searches with the remaining terms as well. The first main contribution of this thesis is to use state of the art models and algorithms to represent the corpus, reduce dimensionality of the representations and hierarchically cluster the representations. Second, this thesis develops analytical metrics to be used in automatic evaluation of the efficacy of the clusterings and in comparisons among model iterations that programmatically remove more and more distractions to the clustering that are discovered in the corpus. Finally, this thesis performs case studies on Hilma to demonstrate the remarkable efficacy of the search extension terms in generating tremendous numbers of additional useful matches, addressing paradigm-based differences in terminology, morphovariance and affixation.
  • Raatikainen, Oona (2021)
    Tämä tutkielma tarkastelee aistiverbien koleksifikaatiotyyppejä Itämeren kielialueen kielissä, eli miten tämän kielialueen kielet erottelevat aistiverbien perusmerkityksiä leksikaalisesti, ja toisaalta mitä perusmerkityksiä kielet ilmaisevat samalla lekseemillä, eli koleksifikoivat. Tutkielma edustaa sekä leksikaalista typologiaa että areaalista kielitiedettä. Aikaisemmassa tutkimuksessa on havaittu areaalisia koleksifikaatiotyyppejä, niin aistiverbien kuin muidenkin semanttisten kenttien kohdalla. Itämeren kielialueen kielet ovat olleet kontaktissa tuhansia vuosia ja niistä löytyy monia areaalisia piirteitä, ulottuen fonologiasta leksikkoon. On myös esitetty, että alueen uralilaiset kielet ovat indoeurooppalaistuneet kontaktin myötä, ja toisaalta alueen indoeurooppalaisista kielistä on löydetty uralilaisia piirteitä. Tämän tutkielman tarkoituksena on tarkastella, onko Itämeren kielialueen kielissä havaittavissa jaettuja aistiverbien koleksifikaatiotyyppejä, ja onko koleksifikaatioissa havaittavissa ns. indoeurooppalaistumista tai uralilaistumista. Tutkielmassa verrataan Itämeren kielialueen kieliä sekä keskenään että verrattuna sukukieliin, joita puhutaan alueen ulkopuolella. Tutkielman aineisto kerättiin kyselylomakkeella, jossa äidinkielisiä puhujia pyydettiin kääntämään omalle äidinkielelleen englanninkielisiä lyhyitä lauseita, joissa esiintyi aistiverbejä. Lopullinen aineisto sisältää 199 vastausta 40 kielellä, joista kahdeksan on uralilaisia kieliä ja 32 Euroopassa puhuttavia indoeurooppalaisia kieliä. Itämeren kielialueen kielistä tutkimuksessa on edustettuna 14 kieltä, jotka kuuluvat viiteen eri kielihaaraan. Itämeren kielialueen ulkopuoliset kielet aineistossa muodostavat kontrolliryhmän, jota vasten kielikontaktien mahdollisia vaikutuksia voidaan verrata. Analyysissä jokaisesta kielestä tunnistettiin mahdolliset koleksifikaatiot, ja kieltenvälinen vertailu tapahtui sekä kielihaaran että -kunnan tasolla. Itämeren kielialueen kieliä verrattiin sekä suhteessa toisiinsa että suhteessa alueen ulkopuolella puhuttuihin sukukieliin. Tutkimuksesta selviää, että Itämeren kielialueen kielet eivät jaa yhtä yhteistä aistiverbien koleksifikaatiotyyppiä, vaan kielistä löytyy useita erilaisia tyyppejä. Tulokset osoittavat myös, että koleksifikaatiotyypit ovat hyvin samanlaisia samaan kielihaaraan kuuluvien lähisukukielten kesken. Osa Itämeren kielialueen kielistä kuitenkin poikkeaa huomattavasti lähisukukielistään, ja koleksifikaatiotyypeistä löytyy yhtäläisyyksiä myös kielisukulaisuusrajojen yli. Sama koleksifikaatiotyyppi löytyy mm. ruotsista, virosta ja meänkielestä, jotka samalla poikkeavat lähisukukielistään. Myöskin latvia ja liettua poikkeavat toisistaan, ja liettuan koleksifikaatiotyyppi muistuttaa slaavilaisista kielistä löytyvää mallia. Osa tuloksista näyttää heijastelevan kielikontaktien vaikutusta. Tutkimuksesta selviää myös, että osa koleksifikaatiotyypeistä on hyvin yleisiä kielikunnasta ja -haarasta riippumatta, joten kielikontakti ei välttämättä ole ainoa yhtäläisyyksiä ja eroavaisuuksia selittävä tekijä.
  • Räikkönen, Nea (2024)
    This thesis examines various colour terms that can be found in the Finno-Ugric languages. The study aims to find and list the most salient colour terms equivalent to the 11 possible basic colour terms in these languages. Etymological background is also provided to varying degrees along with the results. There are 8 Finno-Ugric branches, and the study includes at least one language from each branch, bringing the total to 16 languages. Theoretical background introduces the definition of colour, Berlin and Kay’s basic colour theory, as well as the Finno-Ugric languages. The main source materials for collecting the colour terms vary from dictionaries to research papers to etymological databases, etc. The results of this study are analyzed by comparing them to Berlin and Kay’s basic colour term evolution theory. Recent colour terms and their origins will also be discussed. The main findings show how the colour terms for grey differ from the rest of the colour terms in the final stage of the basic colour term evolution theory. More research should be conducted to see whether this is exclusive to the Finno-Ugric languages, but the results in this study suggest that grey should have its own stage earlier in the basic colour term evolution theory. Another main finding is the lack of distinction between green and blue in North Khanty which should result in there not being distinct terms for colours in the later stages of the theory. North Khanty did, however, have distinct terms for the colours grey and pink. The results also show that the colour purple was missing the most colour terms which would indicate it being the least common or newest colour term in the Finno-Ugric languages. There are many borrowed lexemes in the colour terms. Recent colour terms in the minority languages spoken in Russia are mainly dominated by Russian loanwords, while older loanwords consist of various origins and ages, such as Germanic and Baltic in the Finnic languages, Scandinavian in the Saami languages, and Turkic in the Mari languages and Hungarian.
  • Tapper, Suvi (2023)
    The purpose of this thesis is to examine the prosodic features of English dialects using WaveNet. The exact goal is to investigate whether the differences in prosody between the dialects are present in the data and the results, and whether the geographical distance between the cities included in the data has any influence on this. Another aim is to see how the prosodic features of the sentence types present in the data and their possible differences are manifested in the data and the results. Prosody is concerned with those characteristics of speech which cover more than just individual sounds. Prosodic features can further be divided into paralinguistic features, such as the rate of speech and pausing, and linguistic features, like intonation. Parameters useful for analysing prosody are fundamental frequency (f0), intensity and voice quality – we are interested in the first two. Fundamental frequency is the speed of the vibration of the vocal folds while speaking. Intensity in turn is connected to the changes of air pressure while speaking. The data used for this study is the IViE corpus (Intonational Variation in English), comprising of recordings done in nine British cities – Belfast, Bradford, Cambridge, Cardiff, Dublin, Leeds, Liverpool, London and Newcastle, with approximately 12 speakers per city. In three of the cities, Bradford, Cardiff and London, the dialect is that of a minority. The part of the corpus chosen for this study is a set of 22 sentences consisting of five sentence types. The analysis was performed using WaveNet, a convolutional neural network. It uses causal convolutions to ensure the data is processed correctly. In addition to being conditioned on the output of the network itself, it can also be conditioned using embeddings. The WaveNet implementation used here has two embedding layers – target and normalisation embeddings. Before the analysis the data was pre-processed and the relevant information concerning the fundamental frequency and intensity were extracted from the sound files. A corresponding *.time file was also created for each of the sound files, with the aim of minimising the influence of the possible differences in length between sentences and thus improve the network's ability to recognise the intonation contours correctly. The results are presented in the form of dendrograms, depicting the relationships between the dialects and sentence types – both separately and as a combination of the dialects and sentence types. It was shown, that the differences in prosody were in fact manifested in the data for both dialects and sentence types, although not exactly as expected. The geographical proximity did not seem to influence the dialectal similarities as much as was assumed – in addition to other influences this might also be due to some of the dialects being minority dialects in the cities, and therefore not necessarily so easily comparable to the dialects of the neighbouring area as the majority dialects might have been.
  • McGannon, Steven Nathan (2022)
    This thesis examines the notion of representational content in philosopher Frances Egan’s deflationary account of mental representation (DAMR) for cognitive neuroscience. In particular, this thesis explores to what extent DAMR’s pragmatic account of representational content answers to the content determinacy constraint. The content determinacy constraint is a constraint on an account of mental representation which holds that an account must provide the basis for attributing determinate content to the posited computational states. For example, the constraint requires that an account must specify the conditions under which a given representational content — such a fly — is attributed to a given representational vehicle — such as some particular structures in a frog’s brain. A variety of naturalistic “tracking theories” — broadly, theories which attempt to answer to such a constraint in terms of a privileged naturalistic relation holding between some object and the inner mental state in question — are often held to have thus far failed to satisfactorily meet this constraint. Egan’s deflationary account promises to address this constraint in a way which departs from naturalistic tracking theories (and from several other theories as well). It promises to do this by proffering a notion of representational content which says that such content is fundamentally pragmatic, and that this ultimately allows the account to avoid the problems typically associated with tracking theories. I will examine how DAMR purports to meet the content determinacy constraint via its pragmatic account of content. To this end, I will raise a content indeterminacy concern for one of the pragmatic functions of content DAMR maintains. I will examine several potential lines of response to this indeterminacy concern, some of which I will evaluate as more or less successful. The first chapter introduces the central research aims, methods, and an ethical research statement. The second chapter consists in the theoretical backdrop against which DAMR is situated, in particular, with regard to how the notions of “representation” and “computation” have been employed in cognitive science historically. The third chapter consists in a detailed explication of the components of DAMR, including a careful differentiation between its realist and computational elements and its pragmatic elements. This is followed by an explication of how DAMR purports to meet the content determinacy constraint. The fourth chapter consists in a theoretical concern which suggests some pragmatic elements of DAMR might be vulnerable to a content indeterminacy concern; and, a variety of potential responses to the indeterminacy concern raised. The fifth chapter consists in setting out the central conclusion of the thesis and suggesting four potential areas for future investigation. The central conclusion of this thesis is that DAMR faces a “limited” content indeterminacy concern for at least one of its pragmatic elements. However, I highlight that there are several ambiguities which require resolution prior to consideration if the concern raised extends to other elements of the account. I propose that the results of this thesis demonstrate the need for further clarification with regard to the way in which DAMR is committed to the content determinacy constraint. Ultimately, the concerns raised along with the ambiguities noted should serve to facilitate further philosophical evaluation of DAMR.
  • Williams, Salla (2023)
    Hostility in the player communication of video games (and by extension, mobile games) is a well-documented phenomenon that can have negative repercussions for the well-being of the individual being subjected to it, and the society in general. Existing research on detecting hostility in games through machine learning methods is scarce due to the unavailability of data, imbalanced existing data (few positive samples in a large data set), and the challenges involved in defining and identifying hostile communication. This thesis utilizes communication data from the Supercell game Brawl Stars to produce two distinct machine learning models: a support vector classifier and a multi-layer perceptron. Their performance is compared to each other as well as to that of an existing sentiment analysis classifier, VADER. Techniques such as oversampling and using additional data are also used in an attempt to reach better results by improving the balance of the data set. The support vector classifier model was found to have the best performance overall, with an F1 score of 64.15% when used on the pure data set and 65.74% when combined with the SMOTE oversampling algorithm. The thesis includes an appendix with a list of the words that were found to have the strongest influence on the hostile/non-hostile classification.
  • Wang, Alena (2024)
    This thesis investigates relative clauses in Russian and Belarusian, focusing on syntactic structures, usage patterns, and the distribution of linguistic elements within relative clauses. The study employs a corpus-based approach, analyzing data from the Universal Dependencies (UD) Russian SynTagRus corpus and the Belarusian UD HSE treebank. The research explores various aspects of relative clauses, including the position of the relative clause, the syntactic function of the head, the function of the relativizer, and the part-of-speech distribution within relative clauses. Through quantitative analysis, the study identifies consistent patterns and similarities between Russian and Belarusian relative clauses. Key findings include the predominance of left-headed relative clauses in both languages, with rare instances of right-headed structures primarily occurring in specific linguistic contexts such as correlatives. Nominal subjects emerge as the most frequent syntactic function of the head in both languages, reflecting universal principles governing the syntactic organization of relative clauses. The analysis of relativizers reveals that relative pronouns dominate as the predominant type, with "который" and "якi" being the most prevalent in Russian and Belarusian, respectively. Furthermore, both languages exhibit similar distributions of relative adverbs and conjunctions, indicating a shared syntactic strategy for introducing and connecting subordinate clauses to main clauses. Regarding part-of-speech distribution within relative clauses, nouns and verbs emerge as the most prevalent syntactic relation, highlighting their role in specifying entities and actions. While variations exist, particularly with certain adjective-verb and adverb-noun relations, the overall patterns remain largely similar between Russian and Belarusian.
  • Tarvainen, Jonna (2023)
    Monolingual paraphrases are semantically equivalent sentences in one single language transmitting the same meaning but not necessarily using the same words. Also, the same word can have different meanings in different contexts. Understanding the meaning of a text behind its words is essential for many natural language processing and deep-learning tasks such as machine translation, plagiarism detection, question-answering, and information extraction. Paraphrases have been studied extensively, mainly from an English-only or sometimes multilingual perspective. There are not many studies about paraphrase detection in Finnish and even fewer about detecting paraphrases between different registers of the Finnish language, such as Standard Finnish and Easy Finnish. In this thesis, three different pre-trained sentence-BERT models are tested in a paraphrase detection task. The aim of the task is to find paraphrase pairs and triples between three distinct registers of the Finnish language; Standard Finnish, Easy Finnish, and Colloquial Finnish. As the data Yle News articles in Standard and Easy Finnish mostly from the year 2014 are used, as well as Ylilauta online discussions. The applied BERT models are paraphrase-multilingual-MiniLM-L12-v2 sentence-transformers model and FinBERT model. The first mentioned is also fine-tuned with Finnish paraphrase corpus' data. According to the manual evaluation based on the models' precisions, the fine-tuned model outperforms the other two. The same three models are tested on two different balanced test sets of 50 paraphrase sentence pairs and 50 non-paraphrase sentence pairs. The FinBERT model reaches the best F1 score in this research setting. Among the precision and the F1 score, the average sentence lengths and the repetitiveness of the paraphrase sentence pairs and triples are compared and discussed. The FinBERT model detected the shortest sentences and the most repetition, but its total number of detected sentence pairs was also the highest. As a result of this study, a new Easy Finnish - Standard Finnish paraphrase corpus is collected to facilitate further studies in paraphrase detection or simplification in Finnish. The corpus is presented in this thesis. It contains 5881 sentence pairs of which approximately 98 % can be assumed to be true paraphrases according to the manual evaluation of randomly selected sentence pairs. The corpus is created by using the fine-tuned paraphrase-multilingual-MiniLM -L12-v2 sentence-transformers model and it includes paraphrase sentence pairs from Yle News articles in Easy Finnish and in Standard Finnish from the years 2014-2018.
  • Rouvinen, Alina (2023)
    Smiling is fundamentally human but a more complex phenomenon than might appear at first glance. Studies in the field of language sciences have explored smiling in the context of speech and found that speaking while smiling has perceivable effects on the voice, and this phenomenon is commonly known as “smiling voice”. Although this phenomenon is widely recognised, there is no clear consensus on the precise acoustic characteristics that cue listeners to the presence of a smile. This study aims to investigate whether listeners can identify smiling voice based only on audio stimuli, what prosodic cues or characteristics they might be using to do so, and whether those cues can be extracted and used to replicate smiling voice using speech synthesis. Another aim of this study is to determine whether the level of perceived smiliness can be controlled in synthetic speech. These issues are addressed with the objectives of adding to the understanding of smiling voice in the field of phonetics and exploring the potential of speech synthesis technology for producing expressive speech. A corpus of Finnish speech was used to conduct a preliminary listening experiment where participants compared neutral and positive utterances in a questionnaire and indicated whether the speaker was smiling in the latter. Utterances that were identified as smiley were analysed acoustically to detect prosodic differences between neutral and smiley speech. Based on the results, formant frequencies F2 and F3 and centre of gravity were selected as prosodic cues to control smiling in speech synthesis. The speech synthesiser was a Tacotron 2 system, including a reference encoder, which was already trained on the speech corpus used. Synthesis evaluation was conducted with a second questionnaire where participants listened to the synthesised utterances and indicated how strongly the speaker was smiling. The results of the first questionnaire showed that listeners were able to distinguish neutral and smiley speech, and subsequent acoustic analyses indicated significant effects of smiling on fundamental frequency, formant frequencies, and centre of gravity. Speech synthesis evaluation results further indicated that F2, F3, and centre of gravity can be used to control the level of perceived smiling at least to the extent of a binary distinction. However, the evaluation showed that more sophisticated control of the level of smiling voice was not achieved.