IWSLT.2015 - Papers

[P] [K] Applying cross-entropy difference for selecting parallel training data from publicly available sources for conversational machine translation

[P] [K] Source discriminative word lexicon for translation disambiguation

[P] [K] Phrase-level estimation for machine translation

[P] [K] Improving continuous space language models auxiliary features

[P] [K] Multifeature modular deep neural network acoustic models

[P] [K] Using language adaptive deep neural networks for improved multilingual speech recognition

[P] [K] Punctuation insertion for real-time spoken language translation

[P] [K] Class-based N-gram language difference models for data selection

[P] [K] Morphology-aware alignments for translation to and from a synthetic language

[P] [K] An open-source toolkit for word-level confidence estimation in machine translation

[P] [K] Improving translation of emphasis with pause prediction in speech-to-speech translation systems

[P] [K] Evaluation and revision of a speech translation system for healthcare

[P] [K] Learning segmentations that balance latency versus quality in spoken language translation

[P] [K] Development of a Filipino-to-English bidirectional statistical machine translation system that dynamically updates via user feedback

[P] [K] Parser self-training for syntax-based machine translation

[P] [K] Risk-aware distribution of SMT outputs for translation of documents targeting many anonymous readers

[P] [K] Inducing bilingual lexicons from small quantities of sentence-aligned phonemic transcriptions