Searching Brazilian Twitter for Signs of Mental Health Issues

no code implementations • LREC 2020 • Wesley Santos, Am Funabashi, a, Iv Paraboni, r{\'e}

Depression and related mental health issues are often reflected in the language employed by the individuals who suffer from these conditions and, accordingly, research in Natural Language Processing (NLP) and related fields have developed an increasing number of studies devoted to their recognition in social media text.

text-classification Text Classification

Cross-domain Author Gender Classification in Brazilian Portuguese

no code implementations • LREC 2020 • Rafael Dias, Iv Paraboni, r{\'e}

Author profiling models predict demographic characteristics of a target author based on the text that they have written.

Classification Gender Classification +1

Personality-dependent Neural Text Summarization

no code implementations • RANLP 2019 • Pablo Costa, Iv Paraboni, r{\'e}

In Natural Language Generation systems, personalization strategies - i. e, the use of information about a target author to generate text that (more) closely resembles human-produced language - have long been applied to improve results.

Abstractive Text Summarization Text Generation

Moral Stance Recognition and Polarity Classification from Twitter and Elicited Text

no code implementations • RANLP 2019 • Wesley Santos, Iv Paraboni, r{\'e}

We introduce a labelled corpus of stances about moral issues for the Brazilian Portuguese language, and present reference results for both the stance recognition and polarity classification tasks.

Classification General Classification

Building a Corpus for Personality-dependent Natural Language Understanding and Generation

no code implementations • LREC 2018 • Ricelli Ramos, Georges Neto, Barbara Silva, Danielle Monteiro, Iv Paraboni, r{\'e}, Rafael Dias

Natural Language Understanding Text Generation

Reference production in human-computer interaction: Issues for Corpus-based Referring Expression Generation

no code implementations • LREC 2018 • Danillo Rocha, Iv Paraboni, r{\'e}

Referring Expression Referring expression generation +1

Definite Description Lexical Choice: taking Speaker's Personality into account

no code implementations • LREC 2018 • Alex Lan, Iv Paraboni, r{\'e}

Text Generation

Author Profiling from Facebook Corpora

no code implementations • LREC 2018 • Fern Hsieh, o, Rafael Dias, Iv Paraboni, r{\'e}

Document Classification Word Embeddings

Referring Expression Generation in time-constrained communication

no code implementations • LREC 2018 • Andr{\'e} Mariotti, Iv Paraboni, r{\'e}

Referring Expression Referring expression generation +1

Improving the generation of personalised descriptions

no code implementations • WS 2017 • Thiago Castro Ferreira, Iv Paraboni, r{\'e}

Referring expression generation (REG) models that use speaker-dependent information require a considerable amount of training data produced by every individual speaker, or may otherwise perform poorly.

Referring Expression Referring expression generation +1

Squib: Effects of Cognitive Effort on the Resolution of Overspecified Descriptions

no code implementations • CL 2017 • Iv Paraboni, r{\'e}, Alex Gwo Jen Lan, Matheus Mendes de Sant{'}Ana, Fl{\'a}vio Luiz Coutinho

Studies in referring expression generation (REG) have shown different effects of referential overspecification on the resolution of certain descriptions.

Referring Expression Referring expression generation +1

Zoom: a corpus of natural language descriptions of map locations

no code implementations • IJCNLP 2015 • Romina Altamirano, Thiago Ferreira, Iv Paraboni, r{\'e}, Luciana Benotti

Text Generation

Generating overspecified referring expressions: the role of discrimination

no code implementations • IJCNLP 2015 • Iv Paraboni, r{\'e}, Michelle Galindo, Douglas Iacovelli

Text Generation

Realiza\cc\~ao Superficial baseada em Regras (Rule-based Surface Realisation) [in Portuguese]

no code implementations • WS 2013 • Douglas F. P. da Silva Junior, Eder M. de Novais, Iv Paraboni, r{\'e}

Gera\cc\~ao de instru\cc\~oes em mundos virtuais: primeiros passos (Generation of Instructions in Virtual Worlds: First Steps) [in Portuguese]

no code implementations • WS 2013 • S, Diego Cardozo rim, Felipe Freire, Iv Paraboni, r{\'e}

Gera\cc\~ao de Express\~oes de Refer\^encia usando Rela\cc\~oes Espaciais (Referring Expression Generation Using Spatial Relations) [in Portuguese]

no code implementations • WS 2013 • Diego dos Santos Silva, Iv Paraboni, r{\'e}

Referring Expression Referring expression generation

Portuguese Text Generation from Large Corpora

no code implementations • LREC 2012 • Eder Novais, Iv Paraboni, r{\'e}, Douglas Silva

Among these, there is the issue of data sparseness, a problem that is particularly evident in cases such as our target language - Brazilian Portuguese - which is not only morphologically-rich, but relatively poor in NLP resources such as large, publicly available corpora.

Language Modelling Text Generation

Corpus-based Referring Expressions Generation

no code implementations • LREC 2012 • Hilder Pereira, Eder Novais, Andr{\'e} Mariotti, Iv Paraboni, r{\'e}

In Natural Language Generation, the task of attribute selection (AS) consists of determining the appropriate attribute-value pairs (or semantic properties) that represent the contents of a referring expression.

Attribute Referring Expression +1