First/první Previous/předcházející Home Next/další Last/poslední

MT reshaping the language industry
 03  Volume 1: Research Track




https://www.mtsummit2019.com

Proceedings of Machine Translation Summit XVII
Volume 1: Research Track
Contents
Online Sentence Segmentation for Simultaneous Interpretation using Multi-Shifted Recurrent Neural Network 1
Robust Document Representations for Cross-Lingual Information Retrieval in Low-Resource Settings 12
Enhancing Transformer for End-to-end Speech-to-Text Translation 21
Debiasing Word Embeddings Improves Multimodal Machine Translation 32
Translator2Vec: Understanding and Representing Human Post-Editors 43
Domain Adaptation for MT: A Study with Unknown and Out-of-Domain Tasks 55
What is the impact of raw MT on Japanese users of Word: preliminary results of a usability study using eye-tracking67
MAGMATic: A Multi-domain Academic Gold Standard with Manual Annotation of Terminology for Machine Translation Evaluation 78
Automatic error classi?cation with multiple error labels 87
Interactive-Predictive Neural Machine Translation through Reinforcement and Imitation 96
An Intrinsic Nearest Neighbor Analysis of Neural Machine Translation Architectures 107
Improving Neural Machine Translation Using Noisy Parallel Data through Distillation 118
Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translation 128
Improving Anaphora Resolution in Neural Machine Translation Using Curriculum Learning 140
Improving American Sign Language Recognition with Synthetic Data 151
Selecting Informative Context Sentence by Forced Back-Translation 162
Memory-Augmented Neural Networks for Machine Translation 172
An Exploration of Placeholding in Neural Machine Translation 182
Controlling the Reading Level of Machine Translation Output 193
A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translation 204
The Impact of Preprocessing on Arabic-English Statistical and Neural Machine Translation 214
Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation 222
Identifying Fluently Inadequate Output in Neural and Statistical Machine Translation 233
Character-Aware Decoder for Translation into Morphologically Rich Languages 244
Improving Translations by Combining Fuzzy-Match Repair with Automatic Post-Editing 256
Post-editing Productivity with Neural Machine Translation: An Empirical Assessment of Speed and Quality in the Banking and Finance Domain 267
Post-editese: an Exacerbated Translationese273

First/první Previous/předcházející Články / Articles Next/další Last/poslední

Copyright Ing. Milan Čondák 02.09.2019