No abstract

The success of sentence classification often depends on understanding both the syntactic and semantic properties of wordphrases. Recent progress on this task has been based on exploiting the grammatical structure of sentences but often this structure is difficult to parse and noisy. In this paper, we propose a structureindependent 'Gated Representation Alignment' (GRA) model that blends a phrasefocused Convolutional Neural Network (CNN) approach with sequence-oriented Recurrent Neural Network (RNN). Our novel alignment mechanism allows the RNN to selectively include phrase information in a word-by-word sentence representation, and to do this without awareness of the syntactic structure. An empirical evaluation of GRA shows higher prediction accuracy (up to 4.6%) of finegrained sentiment ratings, when compared to other structure-independent baselines. We also show comparable results to several structure-dependent methods. Finally, we analyzed the effect of our alignment mechanism and found that this is critical to the effectiveness of the CNN-RNN hybrid.

No abstract

The full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. In February 2015, the University of Western Australia organised the First International Conference on Rammed EarthConstruction. The event was a major success with participants from 11 countries. The participants were representatives from the research (scientists, professors, students) and industry worlds (engineers, architects, builders). The conference provided the unique opportunity to present recent advances in rammed earth research, innovative construction practices and sustainable projects in different countries. It also provided the opportunity to discuss the current issues experienced by the rammed earth industry around the world and to create collaborations between research institutions. This paper presents a summary of the discussions held at the forums of the event. It aims to disseminate the priority research topics identified at the conference and to increase awareness of the difficulties currently experienced by the rammed earth industry and by academia.

No abstract