activity
20182022
most citedSEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression

22 citations · 45 across the 3 of their papers we have counts for

collaborators

11 papers

cs.CL20225 cited

Automatic Evaluation and Analysis of Idioms in Neural Machine Translation

Christos Baziotis, Prashant Mathur, Eva Hasler

A major open problem in neural machine translation (NMT) is the translation of idiomatic expressions, such as "under the weather". The meaning of these expressions is not composed…

cs.CL2021

Exploring Unsupervised Pretraining Objectives for Machine Translation

Christos Baziotis, Ivan Titov, Alexandra Birch +1

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches ad…

cs.CL2020

Language Model Prior for Low-Resource Neural Machine Translation

Christos Baziotis, Barry Haddow, Alexandra Birch

The scarcity of large parallel corpora is an important obstacle for neural machine translation. A common solution is to exploit the knowledge of language models (LM) trained on abu…

cs.LG2019

Attention-based Conditioning Methods for External Knowledge Integration

Katerina Margatina, Christos Baziotis, Alexandros Potamianos

In this paper, we present a novel approach for incorporating external knowledge in Recurrent Neural Networks (RNNs). We propose the integration of lexicon features into the self-at…

cs.CL201922 cited

SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression

Christos Baziotis, Ion Androutsopoulos, Ioannis Konstas +1

Neural sequence-to-sequence models are currently the dominant approach in several natural language processing tasks, but require large parallel corpora. We present a sequence-to-se…

cs.CL201918 cited

An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models

Alexandra Chronopoulou, Christos Baziotis, Alexandros Potamianos

A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora. In this paper we present a conceptually simple and effect…