NILC at ASSIN 2: Exploring multilingual approaches

Marco A.Sobrevilla Cabezudo, Marcio Inácio, Ana Carolina Rodrigues, Edresson Casanova, Rogério Figueredo De Sousa

Research output: Contribution to journalConference articlepeer-review


Recognizing Textual Entailment, also known as Natural Language Inference recognition, aims to identify if it is possible to infer the meaning of a text from another fragment of text. In this work, we investigate the use of multilingual models, through BERT, for recognizing inference and similarity in the ASSIN 2 dataset, an entailment recognition and sentence similarity corpus for Portuguese. We also investigate possible features that could enhance the results, such as similarity scores or WordNet relations. Our results show that a multilingual pre-trained BERT model may be su.

Original languageEnglish
Pages (from-to)48-57
Number of pages10
JournalCEUR Workshop Proceedings
StatePublished - 2020
Externally publishedYes
Event2nd ASSIN Shared Task: Evaluating Semantic Textual Similarity and Textual Entailment in Portuguese, ASSIN 2019 - Salvador, Brazil
Duration: 15 Oct 2019 → …


  • BERT
  • Cross-lingual Training
  • Multilingual Training
  • Natural Language Inference


Dive into the research topics of 'NILC at ASSIN 2: Exploring multilingual approaches'. Together they form a unique fingerprint.

Cite this