Cong Duy Vu Hoang

Learn More
Neural encoder-decoder models of machine translation have achieved impressive results, rivalling traditional translation models. However their modelling formulation is overly simplistic, and omits several key inductive biases built into traditional models. In this paper we extend the attentional neural translation model to include structural biases from(More)
Recurrent neural network language models (RNNLM) have recently demonstrated vast potential in modelling long-term dependencies for NLP problems, ranging from speech recognition to machine translation. In this work, we propose methods for conditioning RNNLMs on external side information, e.g., metadata such as keywords, description, document title or topic(More)
We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. The resulting optimisation problem is then tackled using constrained gradient optimisation. Our powerful decoding framework, enables decoding intractable models such as the intersection of left-to-right and rightto-left (bidirectional) as well as(More)
Crowdsourcing has emerged as a new method for obtaining annotations for training models for machine learning. While many variants of this process exist, they largely differ in their method of motivating subjects to contribute and the scale of their applications. To date, however, there has yet to be a study that helps a practitioner to decide what form an(More)
Interactive or Incremental Statistical Machine Translation (IMT) aims to provide a mechanism that allows the statistical models involved in the translation process to be incrementally updated and improved. The source of knowledge normally comes from users who either post-edit the entire translation or just provide the translations for wrongly translated(More)
We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We reformulate decoding, a discrete optimization problem, into a continuous problem, such that optimization can make use of efficient gradient-based techniques. Our powerful decoding framework allows for more accurate decoding for standard neural(More)
OCR (Optical Character Recognition) scanners do not always produce 100% accuracy in recognizing text documents, leading to spelling errors that make the texts hard to process further. This paper presents an investigation for the task of spell checking for OCR-scanned text documents. First, we conduct a detailed analysis on characteristics of spelling errors(More)
In many record matching problems, the input data is either ambiguous or incomplete, making the record matching task difficult. However, for some domains, evidence for record matching decisions are readily available in large quantities on the Web. These resources may be retrieved by making queries to a search engine, making the Web a valuable resource. On(More)
This paper presents an extension of neural machine translation (NMT) model to incorporate additional word-level linguistic factors. Adding such linguistic factors may be of great benefits to learning of NMT models, potentially reducing language ambiguity or alleviating data sparseness problem (Koehn and Hoang, 2007). We explore different linguistic(More)
  • 1