IWSLT.2015 - Papers

#1 Applying cross-entropy difference for selecting parallel training data from publicly available sources for conversational machine translation

#2 Source discriminative word lexicon for translation disambiguation

#3 Phrase-level estimation for machine translation

#4 Improving continuous space language models auxiliary features

#5 Multifeature modular deep neural network acoustic models

#6 Using language adaptive deep neural networks for improved multilingual speech recognition

#7 Punctuation insertion for real-time spoken language translation

#8 Class-based N-gram language difference models for data selection

#9 Morphology-aware alignments for translation to and from a synthetic language

#10 An open-source toolkit for word-level confidence estimation in machine translation

#11 Improving translation of emphasis with pause prediction in speech-to-speech translation systems

#12 Evaluation and revision of a speech translation system for healthcare

#13 Learning segmentations that balance latency versus quality in spoken language translation

#14 Development of a Filipino-to-English bidirectional statistical machine translation system that dynamically updates via user feedback

#15 Parser self-training for syntax-based machine translation

#16 Risk-aware distribution of SMT outputs for translation of documents targeting many anonymous readers

#17 Inducing bilingual lexicons from small quantities of sentence-aligned phonemic transcriptions