22 citations · 73 across the 10 of their papers we have counts for
13 papers
When Does Monolingual Data Help Multilingual Translation: The Role of Domain and Model Scale
Christos Baziotis, Biao Zhang, Alexandra Birch +1
Multilingual machine translation (MMT), trained on a mixture of parallel and monolingual data, is key for improving translation in low-resource language pairs. However, the literat…
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…
Multilingual Machine Translation with Hyper-Adapters
Christos Baziotis, Mikel Artetxe, James Cross +1
Multilingual machine translation suffers from negative interference across languages. A common solution is to relax parameter sharing with language-specific modules like adapters.…
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…
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…
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…
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…
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…
Integrating Recurrence Dynamics for Speech Emotion Recognition
Efthymios Tzinis, Georgios Paraskevopoulos, Christos Baziotis +1
We investigate the performance of features that can capture nonlinear recurrence dynamics embedded in the speech signal for the task of Speech Emotion Recognition (SER). Reconstruc…
NTUA-SLP at IEST 2018: Ensemble of Neural Transfer Methods for Implicit Emotion Classification
Alexandra Chronopoulou, Aikaterini Margatina, Christos Baziotis +1
In this paper we present our approach to tackle the Implicit Emotion Shared Task (IEST) organized as part of WASSA 2018 at EMNLP 2018. Given a tweet, from which a certain word has…
NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs
Christos Baziotis, Nikos Athanasiou, Pinelopi Papalampidi +4
In this paper we present two deep-learning systems that competed at SemEval-2018 Task 3 "Irony detection in English tweets". We design and ensemble two independent models, based on…
NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning
Christos Baziotis, Nikos Athanasiou, Alexandra Chronopoulou +5
In this paper we present deep-learning models that submitted to the SemEval-2018 Task~1 competition: "Affect in Tweets". We participated in all subtasks for English tweets. We prop…
NTUA-SLP at SemEval-2018 Task 2: Predicting Emojis using RNNs with Context-aware Attention
Christos Baziotis, Nikos Athanasiou, Georgios Paraskevopoulos +3
In this paper we present a deep-learning model that competed at SemEval-2018 Task 2 "Multilingual Emoji Prediction". We participated in subtask A, in which we are called to predict…