• Publications
  • Influence
A Comparison of Different Punctuation Prediction Approaches in a Translation Context
TLDR
We test a series of techniques to predict punctuation and its effect on machine translation (MT) quality. Expand
  • 5
  • 2
Character-Word LSTM Language Models
TLDR
We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Expand
  • 37
  • 1
  • PDF
Definite il y a-clefts in spoken French*
ABSTRACT This article discusses il y a-clefts in spoken French. In the linguistic literature, only one function of il y a-clefts is widely acknowledged, namely presenting a new event in theExpand
  • 6
  • 1
Analyzing the Contribution of Top-Down Lexical and Bottom-Up Acoustic Cues in the Detection of Sentence Prominence
TLDR
We investigate how the bottom-up acoustic and top-down lexical cues contribute to sentence prominence by using both types of features in unsupervised and supervised systems for automatic prominence detection. Expand
  • 7
  • PDF
Improving the Translation Environment for Professional Translators
TLDR
We describe the SCATE research with respect to improved fuzzy matching, parallel treebanks, the integration of translation memories with machine translation, quality estimation, terminology extraction from comparable texts, the use of speech recognition in the translation process, and human computer interaction and interface design for the professional translation environment. Expand
  • 4
  • PDF
Language model adaptation for ASR of spoken translations using phrase-based translation models and named entity models
TLDR
Language model adaptation based on Machine Translation (MT) is a recently proposed approach to improve the Automatic Speech Recognition (ASR) of spoken translations that does not suffer from a common problem in approaches based on rescoring. Expand
  • 3
  • PDF
State Gradients for RNN Memory Analysis
TLDR
We propose a framework to investigate what the states of recurrent neural network models (RNNs) remember from their input and for how long. Expand
  • 4
  • PDF
TF-LM: TensorFlow-based Language Modeling Toolkit
TLDR
We present language modeling scripts based on TensorFlow that allow one to train and test competitive models directly, by using a pre-defined configuration or changing it to their needs. Expand
  • 4
  • PDF
Information-Weighted Neural Cache Language Models for ASR
TLDR
Neural cache language models (LMs) extend the idea of regularcache language models by making the cache probability dependent on the similarity between the current context and the context of the words in the cache. Expand
  • 2
  • PDF
STON: Efficient Subtitling in Dutch Using State-of-the-Art Tools
TLDR
We present a modular video subtitling platform that integrates speech/non-speech segmentation, speaker diarisation, language identification, Dutch speech recognition with state-of-the-art acoustic models and language models optimised for efficient subtitled, appropriate preprocessing of the data and alignment of the final result with the video fragment. Expand
  • 3
  • PDF
...
1
2
3
...