Cem Mil Podcasts: A Spoken Portuguese Document Corpus For Multi-modal, Multi-lingual and Multi-Dialect Information Access Research

no code implementations • 23 Sep 2022 • Ekaterina Garmash, Edgar Tanaka, Ann Clifton, Joana Correia, Sharmistha Jat, Winstead Zhu, Rosie Jones, Jussi Karlgren

In this paper we describe the Portuguese-language podcast dataset we have released for academic research purposes.

Descriptive Genre classification

Connecting degree and polarity: An artificial language learning study

1 code implementation • 13 Sep 2021 • Lisa Bylinina, Alexey Tikhonov, Ekaterina Garmash

We investigate a new linguistic generalization in pre-trained language models (taking BERT (Devlin et al., 2019) as a case study).

Language Modelling Sentence

Ensemble Learning for Multi-Source Neural Machine Translation

no code implementations • COLING 2016 • Ekaterina Garmash, Christof Monz

We compare two methods of ensemble set induction: sampling parameter initializations for an NMT system, which is a relatively established method in NMT (Sutskever et al., 2014), and NMT systems translating from different source languages into the same target language, i. e., multi-source ensembles, a method recently introduced by Firat et al. (2016).

Ensemble Learning Machine Translation +2

Bilingual Structured Language Models for Statistical Machine Translation

no code implementations • EMNLP 2015 • Ekaterina Garmash, Christof Monz

Language Modelling Machine Translation +1

Dependency-Based Bilingual Language Models for Reordering in Statistical Machine Translation

no code implementations • EMNLP 2014 • Ekaterina Garmash, Christof Monz

Language Modelling Machine Translation +1