3 papers
cs.CL2020
Romanian Diacritics Restoration Using Recurrent Neural Networks
Stefan Ruseti, Teodor-Mihai Cotet, Mihai Dascalu
Diacritics restoration is a mandatory step for adequately processing Romanian texts, and not a trivial one, as you generally need context in order to properly restore a character.…
cs.CL2019
Answering questions by learning to rank -- Learning to rank by answering questions
George-Sebastian Pîrtoacă, Traian Rebedea, Stefan Ruseti
Answering multiple-choice questions in a setting in which no supporting documents are explicitly provided continues to stand as a core problem in natural language processing. The c…
cs.CL2018
Improving Retrieval-Based Question Answering with Deep Inference Models
George-Sebastian Pirtoaca, Traian Rebedea, Stefan Ruseti
Question answering is one of the most important and difficult applications at the border of information retrieval and natural language processing, especially when we talk about com…