Search Results for author:
Found 30 papers, 2 papers with code
Combination of Neural Machine Translation Systems at WMT20
This paper presents neural machine translation systems and their combination built for the WMT20 English-Polish and Japanese->English translation tasks.
NICT Kyoto Submission for the WMT’21 Quality Estimation Task: Multimetric Multilingual Pretraining for Critical Error Detection
This paper presents the NICT Kyoto submission for the WMT’21 Quality Estimation (QE) Critical Error Detection shared task (Task 3).
NICT Kyoto Submission for the WMT’20 Quality Estimation Task: Intermediate Training for Domain and Task Adaptation
This paper describes the NICT Kyoto submission for the WMT’20 Quality Estimation (QE) shared task.
Fusion of Self-supervised Learned Models for MOS Prediction
This challenge aims to predict MOS scores of synthetic speech on two tracks, the main track and a more challenging sub-track: out-of-domain (OOD).
Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers
MT evaluations in recent papers tend to copy and compare automatic metric scores from previous work to claim the superiority of a method or an algorithm without confirming neither exactly the same training, validating, and testing data have been used nor the metric scores are comparable.
Intermediate Self-supervised Learning for Machine Translation Quality Estimation
The proposed method does not rely on annotated data and is complementary to QE methods involving pre-trained sentence encoders and domain adaptation.
Tagged Back-translation Revisited: Why Does It Really Work?
In this paper, we show that neural machine translation (NMT) systems trained on large back-translated data overfit some of the characteristics of machine-translated texts.
Balancing Cost and Benefit with Tied-Multi Transformers
We propose and evaluate a novel procedure for training multiple Transformers with tied parameters which compresses multiple models into one enabling the dynamic choice of the number of encoder and decoder layers during decoding.
INFODENS: An Open-source Framework for Learning Text Representations
The advent of representation learning methods enabled large performance gains on various language tasks, alleviating the need for manual feature engineering.
DFKI-MLT System Description for the WMT18 Automatic Post-editing Task
This paper presents the Automatic Post-editing (APE) systems submitted by the DFKI-MLT group to the WMT{'}18 APE shared task.
Findings of the WMT 2018 Shared Task on Automatic Post-Editing
In the former subtask, characterized by original translations of lower quality, top results achieved impressive improvements, up to -6. 24 TER and +9. 53 BLEU points over the baseline {``}\textit{do-nothing}{''} system.
Using Explicit Discourse Connectives in Translation for Implicit Discourse Relation Classification
Implicit discourse relation recognition is an extremely challenging task due to the lack of indicative connectives.
General Classification
Implicit Discourse Relation Classification
+4
Common Round: Application of Language Technologies to Large-Scale Web Debates
Web debates play an important role in enabling broad participation of constituencies in social, political and economic decision-taking.
Modeling Diachronic Change in Scientific Writing with Information Density
In this paper we investigate the introduction of information theory inspired features to study long term diachronic change on three levels: lexis, part-of-speech and syntax.
Quality Estimation for Synthetic Parallel Data Generation
This paper presents a novel approach for parallel data generation using machine translation and quality estimation.
