This book constitutes the proceedings of the 14th International Conference on Computational Processing of the Portuguese Language, PROPOR 2020, held in Evora, Portugal, in March 2020. The 36 full papers presented together with 5 short papers were carefully reviewed and selected from 70 submissions. They are grouped in topical sections on speech processing; resources and evaluation; natural language processing applications; semantics; natural language processing tasks; and multilinguality.
INTRODUCTION: TECHNOLOGY MOVES FASTER THAN JOURNALISTIC STANDARDS
1. THE PROBLEM: A JOURNALISTIC MODEL IN TRANSITION
2. ENABLERS: THE AI TECHNOLOGIES DRIVING JOURNALISTIC CHANGE
3. WORKFLOW: A SCALABLE PROCESS FOR NEWSROOM TRANSFORMATION
Will the use of artificial intelligence (AI), algorithms, and smart machines be the end of journalism as we know it-or its savior? In Newsmakers, Francesco Marconi, who has led the development of the Associated Press and Wall Street Journal's use of AI in journalism, offers a new perspective on the potential of these technologies. He explains how reporters, editors, and newsrooms of all sizes can take advantage of the possibilities they provide to develop new ways of telling stories and connecting with readers. Marconi analyzes the challenges and opportunities of AI through case studies ranging from financial publications using algorithms to write earnings reports to investigative reporters analyzing large data sets to outlets determining the distribution of news on social media. Newsmakers contends that AI can augment-not automate-the industry, allowing journalists to break more news more quickly while simultaneously freeing up their time for deeper analysis. Marshaling insights drawn from firsthand experience, Marconi maps a media landscape transformed by artificial intelligence for the better. In addition to considering the benefits of these new technologies, Marconi stresses the continuing need for editorial and institutional oversight. Newsmakers outlines the important questions that journalists and media organizations should consider when integrating AI and algorithms into their workflow. For journalism students as well as seasoned media professionals, Marconi's insights provide much-needed clarity and a practical roadmap for how AI can best serve journalism. (source: Nielsen Book Data)
Life ... but not as we know.- Transmogrification.- Pandemic.- Life on Mars.- Artificial Intelligence.- Attractive Androids.- Big Data.- Faster Than Light Travel.- Antigravity.- Matter Transmission.- The Sub-microscopic World.- Impact Events.
(source: Nielsen Book Data)
This book presents the reader with some of the earliest classic SF short stories - all of them published between 1858 and 1934, featuring both well-known and long-forgotten writers - dealing for the first time with topics to which science had (some) answers only at much later stages. This includes aspects of alien life forms, transmogrification, pandemics, life on Mars, android robots, big data, matter transmission and impact events to name but a few. The short stories are reprinted in full alongside extensive commentaries which also examine some of the latest scientific thinking surrounding the story's main theme and provide the reader with suggestions for further reading. . (source: Nielsen Book Data)
Book — 1 online resource (xvii, 500 pages) : illustrations Digital: text file.PDF.
Corpus Linguistics.- Information Extraction.- Natural Language Processing Applications.- Language Resources.- Sentiment Analysis and Opinion Mining.- Speech Processing.- Syntax and Parsing.
(source: Nielsen Book Data)
This book constitutes the refereed proceedings of the 13th International Conference on Computational Processing of the Portuguese Language, PROPOR 2018, held in Canela, RS, Brazil, in September 2018. The 42 full papers, 3 short papers and 4 other papers presented in this volume were carefully reviewed and selected from 92 submissions. The papers are organized in topical sections named: Corpus Linguistics, Information Extraction, LanguageApplications, Language Resources, Sentiment Analysis and Opinion Mining, Speech Processing, and Syntax and Parsing. (source: Nielsen Book Data)
Book — 1 online resource (xv, 463 pages) Digital: text file.PDF.
Phraseology in translation and contrastive studies.- Lexicography and terminography.- Exploitation of corpora in phraseological studies.- Development of corpora for phraseological studies.- Phraseology and language learning.- Cognitive and cultural aspects of phraseology.- Theoretical and descriptive approaches to phraseology.- Computational approaches to phraseology.
(source: Nielsen Book Data)
This book constitutes the refereed proceedings of the International Conference on Computational and Corpus-Based Phraseology, Europhras 2017, held in London, UK, in November 2017. The 31 full papers presented were carefully reviewed and selected from numerous submissions and are organized into the following thematic sessions: Phraseology in translation and contrastive studies, Lexicography and terminography, Exploitation of corpora in phraseological studies, Development of corpora for phraseological studies, Phraseology and language learning, Cognitive and cultural aspects of phraseology, Theoretical and descriptive approaches to phraseology, and Computational approaches to phraseology. The chapter 'Frequency Consolidation Among Word N-Grams' is available open access under a CC BY 4.0 license. (source: Nielsen Book Data)
Book — 1 online resource (xxi, 205 pages : illustrations
Introduction.- Events and Times.- Temporal Relations.- Relation Labelling Analysis.- Using Temporal Signals.- Using a Framework of Tense and Aspect.- Conclusion.
(source: Nielsen Book Data)
The book offers a detailed guide to temporal ordering, exploring open problems in the field and providing solutions and extensive analysis. It addresses the challenge of automatically ordering events and times in text. Aided by TimeML, it also describes and presents concepts relating to time in easy-to-compute terms. Working out the order that events and times happen has proven difficult for computers, since the language used to discuss time can be vague and complex. Mapping out these concepts for a computational system, which does not have its own inherent idea of time, is, unsurprisingly, tough. Solving this problem enables powerful systems that can plan, reason about events, and construct stories of their own accord, as well as understand the complex narratives that humans express and comprehend so naturally. This book presents a theory and data-driven analysis of temporal ordering, leading to the identification of exactly what is difficult about the task. It then proposes and evaluates machine-learning solutions for the major difficulties. It is a valuable resource for those working in machine learning for natural language processing as well as anyone studying time in language, or involved in annotating the structure of time in documents. (source: Nielsen Book Data)
Book — 1 online resource (xiv, 398 pages) Digital: text file.PDF.
Extending VITHEA in Order to Improve Children's Linguistic Skills
Automatic Classification of the Complexity of Nonfiction Texts in Portuguese for Early School Years
Improving Question-Answering for Portuguese Using Triples Extracted from Corpora
Applying Lexical-Conceptual Knowledge for Multilingual Multi-Document Summarization
Domain-Specific Hybrid Machine Translation from English to Portuguese
Analysis of Temporal Adverbial Phrases for Portuguese-Chinese Machine Translation
Determining the Level of Clients? Dissatisfaction from Their Commentaries
Comparing Approaches for Subjectivity Classification: a Study on Portuguese Tweets
TOPIE: An Open-source Opinion Mining Pipeline to Analyze Consumers' Sentiment in Brazilian Portuguese
Evaluating Progression of Alzheimer?s Disease by Regression and Classification Methods in a Narrative Language Test in Portuguese
A Comparative Evaluation of QA Systems over List Questions
Characterizing Opinion Mining: A Systematic Mapping Study of the Portuguese Language
Finding Compositional Rules for Determining the Semantic Orientation of Phrases
Sentiment Analysis for Brazilian Portuguese over a Skewed Class Corpora
Semantic Relation Extraction. Resources, Tools and Strategies
Extracting and Mining Open Relations from Portuguese Text
Towards Key Phrase Assignment for Texts in Portuguese Language
Entity Linking with Distributional Semantics
Syntax Deep Explorer
Automatic Semantic Role Labeling on Non-revised Syntactic Trees of Journalistic Texts
Improving Coreference Resolution with Semantic Knowledge
Improving POS Tagging across Portuguese Variants with Word Embeddings
Joining Forces for Multiword Expression Identification
A Construction Grammar Approach for Pronominal Clitics in European Portuguese
Investigating Machine Learning Approaches for Sentence Compression in Different Application Contexts for Portuguese
A Model for Textual Entailment Based on Linguistic Rules
Word Embeddings Resources for the Portuguese Language
Making a Virtue of Necessity: A Verb Lexicon
CONTO. PT: Groundwork for the Automatic Creation of a Fuzzy Portuguese Wordnet
Lexical Semantics Annotation for Enriched Portuguese Corpora
Crawling by Readability Level
Towards a Statistical-enriched Corpus Containing Portuguese Collocations in Use: Reviewing Possible Extraction Tools
The Portuguese B2SG: A Semantic Test for Distributional Thesaurus
Automatic Generation of Internet Memes from Portuguese News Titles
FrameNet-Based Automatic Suggestion of Translation Equivalents
Building a Question-Answering Corpus Using Social Media and News Articles
Evaluating Phonetic Spellers for User-generated Content in Brazilian Portuguese
An Automatic Phonetic Aligner for Brazilian Portuguese with a Praat Interface
Design and Analysis of a Database to Evaluate Children's Reading Aloud Performance.
This book constitutes the refereed proceedings of the 12th International Conference on Computational Processing of the Portuguese Language, PROPOR 2016, held in Tomar, Portugal, in July 2016. The 23 full papers and 14 short papers presented in this volume were carefully reviewed and selected from 52 submissions. The papers are organized in topical sections named: language applications, language processing, and language resources.