IAPUCP at SemEval-2021 Task 1: Stacking Fine-Tuned Transformers is Almost All You Need for Lexical Complexity Prediction

no code implementations • SEMEVAL 2021 • Kervy Rivas Rojas, Fernando Alva-Manchego

This paper describes our submission to SemEval-2021 Task 1: predicting the complexity score for single words.

Complex Word Identification Lexical Complexity Prediction +2

Revisiting Neural Language Modelling with Syllables

no code implementations • 24 Oct 2020 • Arturo Oncevay, Kervy Rivas Rojas

Language modelling is regularly analysed at word, subword or character units, but syllables are seldom used.

Language Modelling

Efficient strategies for hierarchical text classification: External knowledge and auxiliary tasks

no code implementations • ACL 2020 • Kervy Rivas Rojas, Gina Bustamante, Arturo Oncevay, Marco A. Sobrevilla Cabezudo

We use the class-definition embeddings as an additional input to condition the prediction of the next layer and in an adapted beam search.

General Classification text-classification +1

Assessing Back-Translation as a Corpus Generation Strategy for non-English Tasks: A Study in Reading Comprehension and Word Sense Disambiguation

no code implementations • WS 2019 • Fabricio Monsalve, Kervy Rivas Rojas, Marco Antonio Sobrevilla Cabezudo, Arturo Oncevay

Corpora curated by experts have sustained Natural Language Processing mainly in English, but the expensiveness of corpora creation is a barrier for the development in further languages.

Machine Translation Reading Comprehension +2