This paper describes the DCU machine translation system in the evaluation campaign of the Joint Fifth Workshop on Statistical Machine Translation and Metrics in ACL-2010. We describe the modular design of our multi-engine machine translation (MT) system with particular focus on the components used in this participation. We participated in the English– Spanish and English–Czech translation tasks...

The problem of optimising the structure of the encoder/decoder pair in a discrete communication system, with an additive distortion measure, is formulated in terms of a quadratic programming (QP) problem. This new formulation benefits from the following special features: it optimises the joint effects of the source/channel coding on the end-to-end distortion; and the encoder and the decoder str...

We propose an attention-enabled encoder-decoder model for the problem of grapheme-to-phoneme conversion. Most previous work has tackled the problem via joint sequence models that require explicit alignments for training. In contrast, the attentionenabled encoder-decoder model allows for jointly learning to align and convert characters to phonemes. With this approach, we achieve state-of-the-art...

Finding typical instances is an effective approach to understand and analyze large data sets. In this paper, we apply the idea of typicality analysis from psychology and cognition science to database query answering, and study the novel problem of answering top-k typicality queries. We model typicality in large data sets systematically. To answer questions like “Who are the top-k most typical N...

We aim to model the results from a selfpaced reading experiment, which tested the effect of semantic type clash and typicality on the processing of German complement coercion. We present two distributional semantic models to test if they can model the effect of both type and typicality in the psycholinguistic study. We show that one of the models, without explicitly representing type informatio...

To achieve the joint active and passive beamforming gains in reconfigurable intelligent surface assisted millimeter wave system, reflected cascade channel needs to be accurately estimated. Many strategies have been proposed literature solve this issue. However, whether Cramér-Rao lower bound (CRLB) of such estimation is achievable still remains uncertain. fill gap, we first convert problem into...

The Maximum Likelihood joint detection of all users in a Multi-Carrier Code Division Multiple Access (MCCDMA) system has a prohibitive complexity, growing exponentially with the number of users, when it is performed using an exhaustive search. In this paper, a novel ML multiuser detection algorithm is proposed, whose complexity is a polynomial function of the number of users and is independent ...

We propose a framework for iterative joint sourcechannel decoding of JPEG2000 codestreams. At the encoder, JPEG2000 is used to perform source coding with certain error resilience (ER) modes, and LDPC codes are used to perform channel coding. During decoding, the source decoder uses the ER modes to identify corrupt sections of the codestream and provides this information to the channel decoder. ...

Joint source-channel decoding based on residual source redundancy is an e ective paradigm for error-resilient data compression. While previous work only considered xed rate systems, the extension of these techniques for variablelength encoded data was recently independently proposed by the authors [6], [7] and by Demir and Sayood [1]. In this paper, we describe and compare the performance of a ...