Page: 1 2 3 4 5 6 7 8... 12
| 61 |
Theodosius “the Greek”, Kliment Smoliatich, and the Unnamed Patriarch
|
|
|
|
BASE
|
|
Show details
|
|
|
| 62 |
Creating a frequency dictionary of spoken Hebrew : a reproducible use of technology to overcome scarcity of data
|
|
|
|
BASE
|
|
Show details
|
|
|
| 63 |
Modelação e prototipagem de ChatBots ; Modeling and prototyping ChatBots
|
|
|
|
Abstract:
Relatório de estágio de mestrado em Matemática e Computação ; Genericamente, ChatBots são programas que interagem com utilizadores humanos através de linguagens naturais. Os ChatBots podem ser criados com objetivos muito diversos, como por exemplo manter uma conversa “inteligente” com um humano, ou prestar serviços em algum domínio concreto, como seja atender chamadas num call-center, reencaminhado-as para um operador. Dada a heterogeneidade dos ChatBots, é importante identificar os seus princípios gerais de organização e de funcionamento. Neste trabalho foi desenvolvida uma proposta original de modelação de ChatBots, que procura identificar estes princípios gerais. Na modelação que desenvolvemos, os ChatBots são organizados em três componentes principais: a interface com o utilizador, o núcleo e o estado do ChatBot. O núcleo é a peça central do funcionamento do Chatbot, pois ele é responsável por processar as interações recebidas do utilizador, gerando reações em resposta. O núcleo contém um conjunto de regras que associam funções de reação a padrões linguísticos que, juntamente com o estado do ChatBot, determinam a escolha da reação a uma dada interação do utilizador. Para a modelação de padrões linguísticos, desenvolvemos aquilo que designamos por expressões regulares linguísticas (ERL). As ERL baseiam-se em expressões regulares, envolvendo etiquetas gramaticais, e incluem um mecanismo para extração das palavras-chave de um padrão linguístico, e deram origem a uma Domain Specific Language. A modelação que desenvolvemos permite a criação de um motor geral para a construção de ChatBots. Para uma prova de conceito, foi criado o Diabrete: um motor geral, open-source, escrito em Python, versão 3, com a base de dados em MySQL, que permite a criação de ChatBots que seguem a modelação desenvolvida neste trabalho. Na implementação do Diabrete recorremos a algumas ferramentas opensource, para levar a cabo as tarefas da análise sintática das frases dos utilizadores (biblioteca FreeLing) e para a construção de um classificador baseado em técnicas de machine learning para a escolha da reação a apresentar a uma dada interação do utilizador (biblioteca NLTK). ; ChatBots are programs that interact with human users through natural languages. ChatBots can be created for very different purposes, such as maintaining an ”inteligent”conversation with a human, or providing services in a specific domain, such as answering calls in a call-center, and forward them to an operator. Given the heterogeneity of ChatBots, it becomes important to identify their general principles of organization and operation. In this work, we identify some of these general principles, and develop a new proposal for the modeling of ChatBots. In the developed model, ChatBots are organized into three main components: the user interface, the core of the ChatBot, and the state of the ChatBot. The core is the centerpiece of Chatbot’s operation, as it is responsible for processing the interactions received from the user, generating reactions in response. The core contains a set of rules that associates reaction functions with linguistic patterns that, together with the state of the ChatBot, determine the choice of reaction to a given user interaction. For modeling linguistic patterns, we develop what we call regular linguistic expressions (ERL). ERLs are based on regular expressions involving grammatical tags, include a mechanism for extracting the keywords from a linguistic standard, and have given rise to a Domain Specific Language. The model that we developed allows the design of a general generator for the construction of ChatBots. For a proof of concept, the Diabrete was created. Diabrete is a general, open-source generator, written in Python, version 3, with the database in MySQL, which allows the construction of ChatBots that follow the modeling developed in this work. In the implementation of Diabrete, we used some opensource tools to perform the tasks of the user-generated sentences (library FreeLing) and to construct a classifier based on machine learning techniques for the choice of reaction to be presented to a given user interaction (library NLTK).
|
|
Keyword:
ChatBot; Ciências Naturais::Matemáticas; Domain specific language; ERL; Generator; Gerador; Linguistic patterns; Modelação; Modeling; Open-source; Padrões linguísticos; Regras; Rules
|
|
URL: http://hdl.handle.net/1822/65020
|
|
BASE
|
|
Hide details
|
|
|
| 64 |
Complejidad textual con fines académicos en el ámbito de la traducción del inglés al español. Variables para su clasificación
|
|
|
|
BASE
|
|
Show details
|
|
|
| 65 |
Reducing Mistranslations in Chinese-English MT Result of Google Translate: An Exploratory Experiment on Source Text Pre-editing by Translators
|
|
Zhao, Yafei. - : The University of Queensland, School of Languages and Cultures, 2018
|
|
BASE
|
|
Show details
|
|
|
| 66 |
A Corpus-based Contrative Study on Semantic Prosody of Persist in - Based on the Self-Built Corpora-Chinese Source Text Corpus and its Translational Corpus and English Political Corpus
|
|
Ma, Wenyue. - : The University of Queensland, School of Languages and Cultures, 2018
|
|
BASE
|
|
Show details
|
|
|
| 67 |
Polish Americans in the History of Bilingual Lexicography: The State of the Art
|
|
|
|
In: Lexikos, Vol 28, Pp 316-342 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
|
| 68 |
Assessing Indonesian students’ competence in translating French texts of different types
|
|
|
|
In: Indonesian Journal of Applied Linguistics, Vol 8, Iss 1, Pp 91-99 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
|
| 69 |
Pyannote.metrics: a toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems
|
|
|
|
In: Annual Conference of the International Speech Communication Association ; https://hal.archives-ouvertes.fr/hal-01836450 ; Annual Conference of the International Speech Communication Association , Aug 2017, Stockholm, Sweden (2017)
|
|
BASE
|
|
Show details
|
|
|
| 70 |
Phonemic transcription of low-resource tonal languages
|
|
|
|
In: ISSN: 1834-7037 ; Australasian Language Technology Association Workshop 2017 ; https://halshs.archives-ouvertes.fr/halshs-01656683 ; Australasian Language Technology Association Workshop 2017, Dec 2017, Brisbane, Australia. pp.53-60 (2017)
|
|
BASE
|
|
Show details
|
|
|
| 71 |
Towards a toolbox to map historical text collections
|
|
|
|
In: 11th Workshop on Geographic Information Retrieval (GIR'17) ; https://hal.archives-ouvertes.fr/hal-01654526 ; 11th Workshop on Geographic Information Retrieval (GIR'17), Nov 2017, Heidelberg, Germany. ⟨10.1145/3155902.3155905⟩ (2017)
|
|
BASE
|
|
Show details
|
|
|
| 72 |
Programming Language Keyword Frequencies Extracted From 16,000,000 Public Github Repositories (October 2016) ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 73 |
Phonemic transcription of low-resource tonal languages
|
|
|
|
In: ISSN: 1834-7037 ; Australasian Language Technology Association Workshop 2017 ; https://halshs.archives-ouvertes.fr/halshs-01656683 ; Australasian Language Technology Association Workshop 2017, Dec 2017, Brisbane, Australia. pp.53-60 (2017)
|
|
BASE
|
|
Show details
|
|
|
| 74 |
Лингвокультурологические особенности английских анекдотов (на материале «Шоу Кэтрин Тейт») ; Linguistic and Cultural Peculiarities of British Jokes (as Exemplified in “The Catherine Tate Show”)
|
|
|
|
BASE
|
|
Show details
|
|
|
| 75 |
Source Monitoring in Bilinguals
|
|
|
|
In: Open Access Theses & Dissertations (2017)
|
|
BASE
|
|
Show details
|
|
|
| 76 |
Developmental Dyslexia and Reading in Spanish as a Foreign Language
|
|
|
|
In: Revista Nebrija de Linguistica Aplicada a la Enseñanza de Lenguas, Vol 11, Iss 23 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
|
| 78 |
Improving subject-verb agreement in SMT
|
|
|
|
In: Vanmassenhove, Eva orcid:0000-0003-1162-820X , Du, Jinhua orcid:0000-0002-3267-4881 and Way, Andy orcid:0000-0001-5736-5930 (2016) Improving subject-verb agreement in SMT. In: Fifth Workshop on Hybrid Approaches to Translation (HyTra), 1 June 2016, Riga, Latvia. (2016)
|
|
BASE
|
|
Show details
|
|
|
| 79 |
Источники изучения истории восточнославянских языков в студиях Ю. Шевелёва
|
|
|
|
BASE
|
|
Show details
|
|
|
Page: 1 2 3 4 5 6 7 8... 12 |
|
