Computational Processing of the Portuguese Language

This book constitutes the proceedings of the 15th International Conference on Computational Processing of the Portuguese Language, PROPOR 2021, held in Fortaleza, Brazil, in March 2021.

The 36 full papers presented together with 4 short papers were carefully reviewed and selected from 88 submissions. They are grouped in topical sections on speech processing; resources and evaluation; natural language processing applications; semantics; natural language processing tasks; and multilinguality.

Inhalt

Resources and Evaluation.- UlyssesNER-Br: a corpus of Brazilian legislative documents for named entity recognition.- A test-suite for the evaluation of Portuguese-English machine translations.- MINT - Mainstream and Independent News Text corpus.- Fakepedia Corpus: a flexible fake news corpus in Portuguese.- A targeted assessment of the syntactic abilities of Transformer models for Galician-Portuguese.- FakeRecogna: A new Brazilian corpus for fake news detection.- Implicit opinion aspect clues in Portuguese texts: analysis and categorization .- CRPC-DB A discourse bank for Portuguese.- Challenges in annotating a treebank of clinical narratives in Brazilian Portuguese.- PetroBERT: a domain adaptation language model for oil and gas applications in Portuguese.- SS-PT: A stance and sentiment data set from Portuguese quoted tweets.- Natural Language Processing Tasks.- ZeroBERTo - leveraging zero-shot text classification by topic modeling.- Banking regulation classification in Portuguese.- Automatic information extraction: a distant reading of the Brazilian Historical-Biographical Dictionary.- Automatic recognition of units of measurement in product descriptions from tax invoices using neural networks.- Entity extraction from Portuguese legal documents using distant supervision.- Sexist hate speech: identifying potential online verbal violence instances.- Book genre classification based on reviews of Portuguese-language Literature.- Combining word embeddings for Portuguese named entity recognition.- BERT for sentiment analysis: pre-trained and fine-tuned alternatives.- Fostering judiciary applications with new fine-tuned models for Legal Named Entity recognition in Portuguese.- Natural Language Processing Applications.- Using topic modeling in classification of Brazilian lawsuits.- PortNOIE: A neural framework for Open Information Extraction for the Portuguese language.- Tracking environmental policy changes in the Brazilian Federal Official Gazette.- A transfer learning analysis of political leaning classification in cross-domain content.- Integrating question answering and text-to-SQL in Portuguese.- Named Entity Extractors for new domains by Transfer Learning with automatically annotated data.- PTT5-Paraphraser: Diversity and meaning fidelity in automatic Portuguese paraphrasing.- Speech Processing and Applications.- A protocol for comparing gesture and prosodic boundaries in multimodal corpora.- Forced phonetic alignment in Brazilian Portuguese using time-delay neural networks.- Brazilian Portuguese speech recognition using Wav2Vec 2.0.- A corpus of neutral voice speech in Brazilian Portuguese.- Comparing lexical and usage frequencies of palatal segments in Portuguese.- Lexical Semantics.- Extracting valences from a dependency treebank for populating the verb lexicon of a Portuguese HPSG grammar.- CQL grammars for lexical and semantic information extraction for Portuguese and Italian.- Drilling Lexico-Semantic Knowledge in Portuguese from BERT.- Short Papers.- The systematic construction of multiple types of corpora through the Lapelinc Framework.- Revisiting CCNET for quality measurements in Galician.- Identifying literary characters in Portuguese: Challenges of an international shared task.- Should I buy or should I pass: e-commerce datasets in Portuguese.- Best MsC/MA & PhD Dissertation.- Abstract meaning representation parsing for the Brazilian Portuguese language.- Enriching Portuguese word embeddings with visual information.-