1 |
Há negociação de sentidos nas interações em fóruns educacionais online? / Is there negotiation of meaning in interactions in online forums?Barbosa, Lorena Lima January 2016 (has links)
BARBOSA, Lorena Lima. Há negociação de sentidos nas interações em fóruns educacionais online? 2016. 190f. - Tese (Doutorado) – Universidade Federal do Ceará, Programa de Pós-graduação em Linguística, Fortaleza (CE), 2016. / Submitted by Gustavo Daher (gdaherufc@hotmail.com) on 2016-10-10T13:03:11Z
No. of bitstreams: 1
2016_tese_llbarbosa.pdf: 1899601 bytes, checksum: 977e96d63e9be1fa31010f2b5d58f85d (MD5) / Approved for entry into archive by Márcia Araújo (marcia_m_bezerra@yahoo.com.br) on 2016-10-11T13:26:46Z (GMT) No. of bitstreams: 1
2016_tese_llbarbosa.pdf: 1899601 bytes, checksum: 977e96d63e9be1fa31010f2b5d58f85d (MD5) / Made available in DSpace on 2016-10-11T13:26:46Z (GMT). No. of bitstreams: 1
2016_tese_llbarbosa.pdf: 1899601 bytes, checksum: 977e96d63e9be1fa31010f2b5d58f85d (MD5)
Previous issue date: 2016 / Based on sociointeractionist theories of second language acquisition, this study aimed at investigating the negotiation of meaning that takes place in online forums of English as a Foreign Language (EFL) courses. Data were collected using aqualitative research methodology which had included some statiscal treatment. First, an instrument was elaborated to analyze the interactions and the negotiation of meaning that take place in online language learning forums. The elaboration of the instrument employed categories borrowed from Conversation Analysis (SEEDHOUSE, 2004), Interaction Patterns (SPADA & FRÖHLICH, 1995), Meaning Negotiation (GASS & e VARONIS, 1985) and Feedback Analysis(BARBOSA, 2011). Next the instrument was tested for its validity. Ten EFL teachers used the elaborated instrument to analyze forum posts of an EFL course organized in 15 (fifteen) interaction blocks of interaction. The answers given by the ten teachers were submitted to two statistical procedures: Cronbach Alpha and Friedman ANOVA. During the validation process, a few modifications were made to the elaborated instrument. The final version obtained the following results: Cronbach Alpha of 0.786 and 0.025–0.031 ANOVA. The final version used in the quantitative analysis served as the starting point for the qualitative analysis of the interactions and of the negotiation of meaning that took place in the online forums of 06 (six) courses of an online English Teaching Certificate Program at UFC-UAB. These courses were grouped into 02 (two) language courses, 02 (two) metalanguage courses and 02 (two) literature courses. Three forums of each course were analyzed for a total of 18 analyzed forums. Results indicated that, in relation to Conversation Patterns, most conversation turns in the analyzed forums were initiated by the tutors, 64.7% of the time (sixty four point seven percent), and conversation sequence was not maintained in most of the forums. In all analyzed forums, only two presented instances of meaning negotiation, and these two instances occurred in forums of the same course. These instances of meaning negotiation happened as the result of either a pseudo inquiry or a true inquiry, or as a response to either some predictable or unpredictable information. In both instances of negotiation, discourse was maintained and unrestricted forms of language were used. Also, in the two instances of meaning negotiation, corrective feedback occurred in one, while in the other there was no corrective feedback. The results of this study support the argument that, in online educational forums, two types of negotiation of meaning can occur: one which is restricted to specific instances of negotiation of the meaning of one word or language form, which interrupts the communication flow of an interaction; and the other, of a broader type (proposed by this researcher), in which two or more participants interact while trying to understand the meaning of a concept or idea. This broader type of negotiation does not depend on feedback to be triggered. In fact, there is no need of a specific trigger, since negotiation can happen as the result of a doubt raised by a student or of a question asked by the tutor or by another student. Results also indicated that corrective feedback, especially of the explicit type, favors a more restricted type of negotiation of the meaning, than of a specific word or language form. / Fundamentada na teoria sociointeracionista de aquisição de segunda língua e nos conceitos de interação e negociação de sentidos, esta pesquisa tem como objetivo geral investigar a negociação de sentidos em fóruns online de disciplinas de língua inglesa, a partir da análise da conversação, dos padrões de interação e do feedback. A fim de atingirmos esse objetivo, realizamos uma análise qualitativa com algum tratamento estatístico, indutiva, de dados interpretativos. Primeiramente, elaboramos um instrumento para análise das interações e negociação de sentidos em fóruns educacionais online, baseado em categorias da análise da conversação (SEEDHOUSE, 2004), da interação (SPADA & FRÖHLICH, 1995), da negociação de sentido (GASS & e VARONIS, 1985) e do feedback (BARBOSA, 2011). Para testarmos a confiabilidade do instrumento elaborado, 10 (dez) professores de Língua Inglesa o utilizaram para analisar mensagens postadas e agrupadas em 15 (quinze) blocos de interação de um fórum de uma disciplina de inglês da Licenciatura a Distância em Letras: Língua Inglesa da UFC/UAB. As respostas fornecidas por esses professores foram submetidos a dois procedimentos estatísticos: o ANOVA de Friedman e o alfa de Cronbach. Após algumas alterações feitas à versão inicial do instrumento, obtivemos o índice alfa de Cronbach de 0,786 e ANOVA, entre 0,025 e 0,031. A versão final do instrumento foi usada para a análise quantitativa que serviu de base para a análise qualitativa da interação e da negociação de sentido em fóruns educacionais online de 06 (seis) disciplinas da licenciatura mencionada. As disciplinas foram agrupadas em três grupos: língua, metalinguagem e literatura. Foram analisadas as interações ocorridas em três fóruns de cada uma das seis disciplinas, totalizando 18 (dezoito) fóruns. Os resultados das análises apontaram que, em relação aos padrões de conversação, a maioria dos turnos nos fóruns analisados foi iniciada pelos tutores, 64,70% (sessenta e quatro vírgula setenta por cento) e que a sequência não foi mantida na maioria dos fóruns. Em todos os fóruns analisados, apenas dois blocos apresentaram instâncias de negociação de sentido, sendo essas instâncias em uma única disciplina. A negociação de sentido ocorreu tanto a partir de um pseudo-pedido, um pedido autêntico, uma informação imprevisível ou uma informação previsível. Observamos também que, nos dois casos de negociação de sentidos, ocorreu discurso mantido e uso irrestrito das formas linguísticas. Ainda, nas instâncias de negociação de sentidos, evidenciamos a ocorrência do feedback corretivo em um dos blocos, enquanto que no outro bloco não houve feedback. Com base nas análises empreendidas, defendemos a tese de que, em fóruns educacionais online, podem ocorrer dois tipos de negociação de sentido: um tipo mais restrito a instâncias específicas de negociação de algum termo ou estrutura que gera uma quebra no fluxo comunicacional; e um tipo mais amplo (proposto pela pesquisadora) em que os interlocutores se engajam em uma negociação visando discutir e compreender um determinado conceito. Quando a negociação de sentido acontece em seu sentido mais amplo, não há necessidade de que haja um feedback na posição de indicador. Na verdade, o indicador pode nem existir, uma vez que o conceito pode ser criado a partir de uma dúvida de um aluno ou de uma pergunta feita pelo tutor ou outro participante da interação. Em relação à negociação de uma palavra ou estrutura específica, acreditamos que o feedback corretivo, principalmente o explícito, seja mais favorável a negociação por apontar diretamente o erro do aluno, facilitando sua identificação.
|
2 |
Online Teacherpreneurship: Shedding Light on the Practice, the Individuals Who Pursue It, and the Impacts They ExperienceJanuary 2018 (has links)
abstract: Online teacherpreneurs are current and former PreK-12 teachers who share their original classroom resources in online marketplaces where teachers download them for a small fee. Online teacherpreneurs’ resources are becoming prolific in classrooms today. Meanwhile, online teacherpreneurs stand to gain financially and professionally. This exploratory study drew on conceptual frameworks from entrepreneurship and teacher leadership to describe the practice of online teacherpreneurship in terms of the characteristics of the people who participate, the school environments in which they work, and the possible impacts they experience. An exploratory sequential mixed methods design was used. In phase one, 10 semi-structured interviews were conducted with online teacherpreneurs who ranked in the top 1% of sellers on TeachersPayTeachers.com for profits earned. In phase two, the results of the interviews were used to develop a quantitative survey, which was distributed to an international sample of 412 TeachersPayTeachers.com sellers with various levels of experience and sales success. Results from both phases were analyzed separately and together, indicating that online teacherpreneurs viewed themselves as helpful, hard-working, creative, and organized. While some online teacherpreneurs worked in supportive school environments, others worked in unsupportive or ambivalent schools. Most online teacherpreneurs kept their online business and classroom teaching separate. They reported that online teacherpreneurship involved a variety of practices including creating educational resources, collaborating with teachers, collaborating with fellow teacherpreneurs, and engaging in entrepreneurial endeavors such as marketing. They also believed they experienced impacts including improvements to teaching practice, teacher leadership opportunities, and some professional stressors. Implications for online teacherpreneurs and other stakeholders including teachers, school and district leaders, and teacher educators are considered. / Dissertation/Thesis / Doctoral Dissertation Learning, Literacies and Technologies 2018
|
3 |
Usability Testing for e-Portfolio Websites in an Academic Environment: A Qualitative Study / Usability Testing for ePortfolio Websites in an Academic EnvironmentReborn, Jaime 12 1900 (has links)
Many academic institutions are tasked with trying to improve the usability of their online educational support technologies such as ePortfolios, intelligent websites, and other interface technology to make them as efficient as possible to meet the requirements of their end users. This is particularly important for the academic institutions during times and situations when they may not have a live human presence available to respond to various inquiries from their end users about the technology. The challenges of an academic institution in making its ePortfolios viable can cost itself, its end users, as well as its other stakeholders, money, time, and confidence in the technology. This study is about usability testing for improving the user-interface for ePortfolios. This is a qualitative study using the think-aloud protocol (TAP) for data collection and failure modes and effects analysis (FMEA) for data analysis.
|
4 |
HÃ negociaÃÃo de sentidos nas interaÃÃes em fÃruns educacionais online? / Is there negotiation of meaning in interactions in online forums?Lorena Lima Barbosa 01 July 2016 (has links)
nÃo hà / Fundamentada na teoria sociointeracionista de aquisiÃÃo de segunda lÃngua e nos conceitos de interaÃÃo e negociaÃÃo de sentidos, esta pesquisa tem como objetivo geral investigar a negociaÃÃo de sentidos em fÃruns online de disciplinas de lÃngua inglesa, a partir da anÃlise da conversaÃÃo, dos padrÃes de interaÃÃo e do feedback. A fim de atingirmos esse objetivo, realizamos uma anÃlise qualitativa com algum tratamento estatÃstico, indutiva, de dados interpretativos. Primeiramente, elaboramos um instrumento para anÃlise das interaÃÃes e negociaÃÃo de sentidos em fÃruns educacionais online, baseado em categorias da anÃlise da conversaÃÃo (SEEDHOUSE, 2004), da interaÃÃo (SPADA & FRÃHLICH, 1995), da negociaÃÃo de sentido (GASS & e VARONIS, 1985) e do feedback (BARBOSA, 2011). Para testarmos a confiabilidade do instrumento elaborado, 10 (dez) professores de LÃngua Inglesa o utilizaram para analisar mensagens postadas e agrupadas em 15 (quinze) blocos de interaÃÃo de um fÃrum de uma disciplina de inglÃs da Licenciatura a DistÃncia em Letras: LÃngua Inglesa da UFC/UAB. As respostas fornecidas por esses professores foram submetidos a dois procedimentos estatÃsticos: o ANOVA de Friedman e o alfa de Cronbach. ApÃs algumas alteraÃÃes feitas à versÃo inicial do instrumento, obtivemos o Ãndice alfa de Cronbach de 0,786 e ANOVA, entre 0,025 e 0,031. A versÃo final do instrumento foi usada para a anÃlise quantitativa que serviu de base para a anÃlise qualitativa da interaÃÃo e da negociaÃÃo de sentido em fÃruns educacionais online de 06 (seis) disciplinas da licenciatura mencionada. As disciplinas foram agrupadas em trÃs grupos: lÃngua, metalinguagem e literatura. Foram analisadas as interaÃÃes ocorridas em trÃs fÃruns de cada uma das seis disciplinas, totalizando 18 (dezoito) fÃruns. Os resultados das anÃlises apontaram que, em relaÃÃo aos padrÃes de conversaÃÃo, a maioria dos turnos nos fÃruns analisados foi iniciada pelos tutores, 64,70% (sessenta e quatro vÃrgula setenta por cento) e que a sequÃncia nÃo foi mantida na maioria dos fÃruns. Em todos os fÃruns analisados, apenas dois blocos apresentaram instÃncias de negociaÃÃo de sentido, sendo essas instÃncias em uma Ãnica disciplina. A negociaÃÃo de sentido ocorreu tanto a partir de um pseudo-pedido, um pedido autÃntico, uma informaÃÃo imprevisÃvel ou uma informaÃÃo previsÃvel. Observamos tambÃm que, nos dois casos de negociaÃÃo de sentidos, ocorreu discurso mantido e uso irrestrito das formas linguÃsticas. Ainda, nas instÃncias de negociaÃÃo de sentidos, evidenciamos a ocorrÃncia do feedback corretivo em um dos blocos, enquanto que no outro bloco nÃo houve feedback. Com base nas anÃlises empreendidas, defendemos a tese de que, em fÃruns educacionais online, podem ocorrer dois tipos de negociaÃÃo de sentido: um tipo mais restrito a instÃncias especÃficas de negociaÃÃo de algum termo ou estrutura que gera uma quebra no fluxo comunicacional; e um tipo mais amplo (proposto pela pesquisadora) em que os interlocutores se engajam em uma negociaÃÃo visando discutir e compreender um determinado conceito. Quando a negociaÃÃo de sentido acontece em seu sentido mais amplo, nÃo hà necessidade de que haja um feedback na posiÃÃo de indicador. Na verdade, o indicador pode nem existir, uma vez que o conceito pode ser criado a partir de uma dÃvida de um aluno ou de uma pergunta feita pelo tutor ou outro participante da interaÃÃo. Em relaÃÃo à negociaÃÃo de uma palavra ou estrutura especÃfica, acreditamos que o feedback corretivo, principalmente o explÃcito, seja mais favorÃvel a negociaÃÃo por apontar diretamente o erro do aluno, facilitando sua identificaÃÃo. / Based on sociointeractionist theories of second language acquisition, this study aimed at investigating the negotiation of meaning that takes place in online forums of English as a Foreign Language (EFL) courses. Data were collected using aqualitative research methodology which had included some statiscal treatment. First, an instrument was elaborated to analyze the interactions and the negotiation of meaning that take place in online language learning forums. The elaboration of the instrument employed categories borrowed from Conversation Analysis (SEEDHOUSE, 2004), Interaction Patterns (SPADA & FRÃHLICH, 1995), Meaning Negotiation (GASS & e VARONIS, 1985) and Feedback Analysis(BARBOSA, 2011). Next the instrument was tested for its validity. Ten EFL teachers used the elaborated instrument to analyze forum posts of an EFL course organized in 15 (fifteen) interaction blocks of interaction. The answers given by the ten teachers were submitted to two statistical procedures: Cronbach Alpha and Friedman ANOVA. During the validation process, a few modifications were made to the elaborated instrument. The final version obtained the following results: Cronbach Alpha of 0.786 and 0.025â0.031 ANOVA. The final version used in the quantitative analysis served as the starting point for the qualitative analysis of the interactions and of the negotiation of meaning that took place in the online forums of 06 (six) courses of an online English Teaching Certificate Program at UFC-UAB. These courses were grouped into 02 (two) language courses, 02 (two) metalanguage courses and 02 (two) literature courses. Three forums of each course were analyzed for a total of 18 analyzed forums. Results indicated that, in relation to Conversation Patterns, most conversation turns in the analyzed forums were initiated by the tutors, 64.7% of the time (sixty four point seven percent), and conversation sequence was not maintained in most of the forums. In all analyzed forums, only two presented instances of meaning negotiation, and these two instances occurred in forums of the same course. These instances of meaning negotiation happened as the result of either a pseudo inquiry or a true inquiry, or as a response to either some predictable or unpredictable information. In both instances of negotiation, discourse was maintained and unrestricted forms of language were used. Also, in the two instances of meaning negotiation, corrective feedback occurred in one, while in the other there was no corrective feedback. The results of this study support the argument that, in online educational forums, two types of negotiation of meaning can occur: one which is restricted to specific instances of negotiation of the meaning of one word or language form, which interrupts the communication flow of an interaction; and the other, of a broader type (proposed by this researcher), in which two or more participants interact while trying to understand the meaning of a concept or idea. This broader type of negotiation does not depend on feedback to be triggered. In fact, there is no need of a specific trigger, since negotiation can happen as the result of a doubt raised by a student or of a question asked by the tutor or by another student. Results also indicated that corrective feedback, especially of the explicit type, favors a more restricted type of negotiation of the meaning, than of a specific word or language form.
|
5 |
Comparison Of Learning Experiences And Outcomes Between A Serious Game-based And Non-game-based Online American History CourseHess, Taryn 01 January 2010 (has links)
The use of online courses continues to increase despite the small amount of research that exists on the effectiveness of online educational environments. The little research that has been conducted has focused on evaluating factors taken into consideration during the adoption of online learning environments. One notable benefit often cited is the ability to incorporate multimedia such as video games. Although game researchers and developers are pushing for the use of video games for educational purposes, there is a lack of research on the effectiveness of serious video games. When paring the increasing use of online educational environments, the push to use serious video games, and the lack of research on the effectiveness of online learning environments and video games, there is a clear need for further investigation into the use of serious video games in an online format. Based on current literature, no other known study has conducted an analysis comparing a serious game-based and non-game based online course; making this a unique study. The purpose of this study was to compare student learning experiences and outcomes between a serious game-based and non-game based online American History course. The data sources were data provided from Florida Virtual School (FLVS) and student and teacher interviews. Random samples of 92 students were statistically analyzed. A group of 8 students and 4 teachers were interviewed. FLVS data provided were analyzed using an independent t-test and the Mann-Whitney test and the student and teacher interview were analyzed using thematic analysis. Results of an independent t-test revealed that there was a significant (p > .01) difference in the mean number of days necessary to complete the course (MGB = 145.80, SDGB = 50.64, MNGB = 112.63, SDNGB = 49.60). The Mann-Whitney results indicated a significant difference between course performance and the type of American history course (Z = -5.066, p > .01); students in the serious game-based online course had an A average whereas students in the non-game-based online course had a B average. The thematic analysis of the relationship between student performance and motivation in both courses indicated that students and teachers of the game-based online course provided more reasons for student motivation than the students and teachers in the non-game-based online course. The thematic analysis of what aspects do students perceive as helpful and/or hindering to their learning indicated that students and teachers of the game-based online course provided more desirable, more helpful, less undesirable, and less hindering aspects for their course than the students and teachers in the non-game-based online course. As a result of the unique nature of this study, the findings provide new information for the fields of research on online learning, serious video gaming, and instructional design as well as inform instructional-designers, teachers, education stakeholders, serious video game designers, and education researchers.
|
6 |
Game-Theoretic Analysis of Strategic Behaviour in Networks, Crowds and ClassroomsVallam, Rohith Dwarakanath January 2014 (has links) (PDF)
Over the past decade, the explosive growth of the Internet has led to a surge of interest to understand and predict aggregate behavior of large number of people or agents, particularly when they are connected through an underlying network structure. Numerous Internet-based applications have emerged that are as diverse as getting micro-tasks executed through online labor markets (also known as crowd sourcing) to acquiring new skills through massively open online courses (also known as MOOCs). However, there has been a major inadequacy in existing studies with respect to evaluating the impact of strategic behavior of the agents participating in such networks, crowds, and classrooms. The primary focus of this doctoral work is to understand the equilibrium behaviour emerging from these real-world, strategic environments by blending ideas from the areas of game theory, graph theory, and optimization, to derive novel solutions to these new-age economic models. In particular, we investigate the following three research challenges:
(1) How do strategic agents form connections with one another? Will it ever happen that strategically stable networks are social welfare maximizing as well?
(2) How do we design mechanisms for eliciting truthful feedback about an object (perhaps a new product or service or person) from a crowd of strategic raters? What can we tell about these mechanisms when the raters are connected through a social network?
(3) How do we incentivize better participation of instructors and students in online edu-cation forums? Can we recommend optimal strategies to students and instructors to get the best out of these forums?
|
7 |
Confidence Measures for Automatic and Interactive Speech RecognitionSánchez Cortina, Isaías 07 March 2016 (has links)
[EN] This thesis work contributes to the field of the {Automatic Speech Recognition} (ASR). And particularly to the {Interactive Speech Transcription} and {Confidence Measures} (CM) for ASR.
The main goals of this thesis work can be summarised as follows:
1. To design IST methods and tools to tackle the problem of improving automatically generated transcripts.
2. To assess the designed IST methods and tools on real-life tasks of transcription in large educational repositories of video lectures.
3. To improve the reliability of the IST by improving the underlying (CM).
Abstracts:
The {Automatic Speech Recognition} (ASR) is a crucial task in a broad range of important applications which could not accomplished by means of manual transcription. The ASR can provide cost-effective transcripts in scenarios of increasing social impact such as the {Massive Open Online Courses} (MOOC), for which the availability of accurate enough is crucial even if they are not flawless. The transcripts enable search-ability, summarisation, recommendation, translation; they make the contents accessible to non-native speakers and users with impairments, etc. The usefulness is such that students improve their academic performance when learning from subtitled video lectures even when transcript is not perfect.
Unfortunately, the current ASR technology is still far from the necessary accuracy.
The imperfect transcripts resulting from ASR can be manually supervised and corrected, but the effort can be even higher than manual transcription.
For the purpose of alleviating this issue, a novel {Interactive Transcription of Speech} (IST) system is presented in this thesis. This IST succeeded in reducing the effort if a small quantity of errors can be allowed; and also in improving the underlying ASR models in a cost-effective way.
In other to adequate the proposed framework into real-life MOOCs,
another intelligent interaction methods involving limited user effort were investigated. And also, it was introduced a new method which benefit from the user interactions to improve automatically the unsupervised parts ({Constrained Search} for ASR).
The conducted research was deployed into a web-based IST platform with which it was possible to produce a massive number of semi-supervised lectures from two different well-known repositories, videoLectures.net and poliMedia.
Finally, the performance of the IST and ASR systems can be easily increased by improving the computation of the {Confidence Measure} (CM) of transcribed words. As so, two contributions were developed:
a new particular {Logistic Regresion} (LR) model;
and the speaker adaption of the CM for cases in which it is possible, such with MOOCs. / [ES] Este trabajo contribuye en el campo del {reconocimiento automático del habla} (RAH). Y en especial, en el de la {transcripción interactiva del habla} (TIH) y el de las {medidas de confianza} (MC) para RAH. Los objetivos principales son los siguientes:
1. Diseño de métodos y herramientas TIH para mejorar las transcripciones automáticas.
2. Evaluar los métodos y herramientas TIH empleando tareas de transcripción realistas extraídas de grandes repositorios de vídeos educacionales.
3. Mejorar la fiabilidad del TIH mediante la mejora de las MC.
Resumen:
El {reconocimiento automático del habla} (RAH) es una tarea crucial en una amplia gama de aplicaciones importantes que no podrían realizarse mediante transcripción manual. El RAH puede proporcionar transcripciones rentables en escenarios de creciente impacto social como el de los {cursos abiertos en linea masivos} (MOOC), para el que la disponibilidad de transcripciones es crucial, incluso cuando no son completamente perfectas. Las transcripciones permiten la automatización de procesos como buscar, resumir, recomendar, traducir; hacen que los contenidos sean más accesibles para hablantes no nativos y usuarios con discapacidades, etc. Incluso se ha comprobado que mejora el rendimiento de los estudiantes que aprenden de videos con subtítulos incluso cuando estos no son completamente perfectos.
Desafortunadamente, la tecnología RAH actual aún está lejos de la precisión necesaria.
Las transcripciones imperfectas resultantes del RAH pueden ser supervisadas y corregidas manualmente, pero el esfuerzo puede ser incluso superior al de la transcripción manual. Con el fin de aliviar este problema, esta tesis presenta un novedoso sistema de {transcripción interactiva del habla} (TIH).
Este método TIH consigue reducir el esfuerzo de semi-supervisión siempre que sea aceptable una pequeña cantidad de errores; además mejora a la par los modelos RAH subyacentes.
Con objeto de transportar el marco propuesto para MOOCs, también se investigaron otros métodos de interacción inteligentes que involucran esfuerzo limitado por parte del usuario. Además, se introdujo un nuevo método que aprovecha las interacciones para mejorar aún más las partes no supervisadas (ASR con {búsqueda restringida}).
La investigación en TIH llevada a cabo se desplegó en una plataforma web con el que fue posible producir un número masivo de transcripciones de videos de dos conocidos repositorios, videoLectures.net y poliMedia.
Por último, el rendimiento de la TIH y los sistemas de RAH se puede aumentar directamente mediante la mejora de la estimación de la {medida de confianza} (MC) de las palabras transcritas. Por este motivo se desarrollaron dos contribuciones: un nuevo modelo discriminativo {logístico} (LR);
y la adaptación al locutor de la MC para los casos en que es posible, como por ejemplo en MOOCs. / [CA] Aquest treball hi contribueix al camp del {reconeixment automàtic de la parla} (RAP).
I en especial, al de la {transcripció interactiva de la parla} i el de {mesures de confiança} (MC) per a RAP.
Els objectius principals són els següents:
1. Dissenyar mètodes i eines per a TIP per tal de millorar les transcripcions automàtiques.
2. Avaluar els mètodes i eines TIP per a tasques de transcripció realistes extretes de grans repositoris de vídeos educacionals.
3. Millorar la fiabilitat del TIP, mitjançant la millora de les MC.
Resum:
El {reconeixment automàtic de la parla} (RAP) és una tasca crucial per una àmplia gamma d'aplicacions importants que no es poden dur a terme per mitjà de la transcripció manual. El RAP pot proporcionar transcripcions en escenaris de creixent impacte social com els {cursos online oberts massius} (MOOC). Les transcripcions permeten automatitzar tasques com ara cercar, resumir, recomanar, traduir; a més a més,
fa accessibles els continguts als parlants no nadius i els usuaris amb discapacitat, etc. Fins i tot, pot millorar el rendiment acadèmic de estudiants que aprenen de xerrades amb subtítols, encara que aquests subtítols no siguen perfectes. Malauradament, la tecnologia RAP actual encara està lluny de la precisió necessària.
Les transcripcions imperfectes resultants de RAP poden ser supervisades i corregides manualment, però aquest l'esforç pot acabar sent superior a la transcripció manual. Per tal de resoldre aquest problema, en aquest treball es presenta un sistema nou per a {transcripció interactiva de la parla} (TIP). Aquest sistema TIP va ser reeixit en la reducció de l'esforç per quan es pot permetre una certa quantitat d'errors;
així com també en en la millora dels models RAP subjacents.
Per tal d'adequar el marc proposat per a MOOCs, també es van investigar altres mètodes d'interacció intel·ligents amb esforç d''usuari limitat.
A més a més, es va introduir un nou mètode que aprofita les interaccions per tal de millorar encara més les parts no supervisades (RAP amb {cerca restringida}).
La investigació en TIP duta a terme es va desplegar en una plataforma web amb la qual va ser possible produir un nombre massiu de transcripcions semi-supervisades de xerrades de repositoris ben coneguts, videoLectures.net i poliMedia.
Finalment, el rendiment de la TIP i els sistemes de RAP es pot augmentar directament mitjançant la millora de l'estimació de la {Confiança Mesura} (MC) de les paraules transcrites. Per tant, es van desenvolupar dues contribucions: un nou model discriminatiu logístic (LR);
i l'adaptació al locutor de la MC per casos en que és possible, per exemple amb MOOCs. / Sánchez Cortina, I. (2016). Confidence Measures for Automatic and Interactive Speech Recognition [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/61473
|
Page generated in 0.1127 seconds