Duygu Ataman

TL;DR: This paper proposed a new vocabulary reduction method for NMT, which can reduce the vocabulary of a given input corpus at any rate while also considering the morphological properties of the language, and achieved a significant improvement of 2.3 BLEU points over the conventional vocabulary reduction technique, showing that it can provide better accuracy in open vocabulary translation of morphologically rich languages.

TL;DR: The authors propose to replace the source-language embedding layer of NMT with a bi-directional recurrent neural network that generates compositional representations of the input at any desired level of granularity.

TL;DR: An extensive evaluation of two unsupervised vocabulary reduction methods in NMT, the wellknown byte-pair-encoding (BPE) and linguistically-motivated vocabulary reduction (LMVR), a segmentation method which also considers morphological properties of subwords.

TL;DR: The authors propose to replace the source-language embedding layer of NMT with a bi-directional recurrent neural network that generates compositional representations of the input at any desired level of granularity.

TL;DR: In this paper, the authors manually audit the quality of 205 language-specific corpora released with five major public datasets (CCAligned, ParaCrawl, WikiMatrix, OSCAR, mC4) and audit the correctness of language codes in a sixth (JW300).