Deep-XFCT: Deep learning 3D-mineral liberation analysis with micro X-ray fluorescence and computed tomography

The rapid development of X-ray micro-computed tomography (micro-CT) opens new opportunities for 3D analysis of particle and grain-size characterisation, determination of particle densities and shape factors, estimation of mineral associations and liberation and locking. Current practices in mineral liberation analysis are based on 2D representations leading to systematic errors in the extrapolation to volumetric properties. New quantitative methods based on tomographic data are therefore urgently required for characterisation of mineral deposits, mineral processing, characterisation of tailings, rock typing, stratigraphic refinement, reservoir characterisation for applications in the resource industry, environmental and material sciences. To date, no simple non-destructive method exists for 3D mineral liberation analysis. We present a new development based on combining micro-CT with micro-X-ray fluorescence (micro-XRF) using deep learning. We demonstrate successful semi-automated multi-modal analysis of a crystalline magmatic rock where the new technique overcomes the difficult task of differentiating feldspar from quartz in micro-CT data set. The approach is universal and can be extended to any multi-modal and multi-instrument analysis for further refinement. We conclude that the combination of micro-CT and micro-XRF already provides a new opportunity for robust 3D mineral liberation analysis in both field and laboratory applications.

A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning

Structured belief states are crucial for user goal tracking and database query in task-oriented dialog systems. However, training belief trackers often requires expensive turn-level annotations of every user utterance. In this paper we aim at alleviating the reliance on belief state labels in building end-to-end dialog systems, by leveraging unlabeled dialog data towards semi-supervised learning. We propose a probabilistic dialog model, called the LAtent BElief State (LABES) model, where belief states are represented as discrete latent variables and jointly modeled with system responses given user inputs. Such latent variable modeling enables us to develop semi-supervised learning under the principled variational learning framework. Furthermore, we introduce LABES-S2S, which is a copy-augmented Seq2Seq model instantiation of LABES. In supervised experiments, LABES-S2S obtains strong results on three benchmark datasets of different scales. In utilizing unlabeled dialog data, semi-supervised LABES-S2S significantly outperforms both supervised-only and semi-supervised baselines. Remarkably, we can reduce the annotation demands to 50% without performance loss on MultiWOZ.