There has been a recent line of work automatically learning scripts from unstructured texts, by modeling narrative event chains. While the dominant approach group events using event pair relations, LSTMs have been used to encode full chains of narrative events. The latter has the advantage of learning long-range temporal orders 1 , yet the former is more adaptive to partial orders. We propose a neural model that leverages the advantages of both methods, by using LSTM hidden states as features for event pair modelling. A dynamic memory network is utilized to automatically induce weights on existing events for inferring a subsequent event. Standard evaluation shows that our method significantly outperforms both methods above, giving the best results reported so far.

Carotenoids are one of the widespread and ubiquitous lipid-soluble pigments that produce a wide range of colours which are universally found in various plants, microalgae, bacteria and fungi. Recently, interest in using carotenoids as feed ingredients has increased markedly owing to their bioactive and health-promoting properties. In terms of applications, carotenoid-rich products are widely available in the form of food and feed additive, supplements and natural colourants. Carotenoids play a versatile biological role that contributes to therapeutic effects, including anticancer, immunomodulators, anti-inflammatory, antibacterial, antidiabetic and neuroprotective. Dietary supplementation of carotenoids not only improves the production performance and health of poultry birds, but also enhances the quality of egg and meat. Several studies have suggested that the supplementation of plant derived carotenoids revealed numerous health-promoting activities in poultry birds. Carotenoids reduce the oxidative stress in pre-hatched and post-hatched birds through different mechanisms, including quench free radicals, activating antioxidant enzymes and inhibiting the signalling pathways. Use of carotenoids in poultry feed as a part of nutrient that confers bird health and improve product quality. Carotenoids play a critical role for the pigmentation of egg yolk, skin, legs, beak, comb, feather and fat. Birds consumed carotenoid deficient diet resulting hues of their egg yolk or pale coloured skin. Therefore, uniform pigmentation generally indicates the health status and quality of the poultry products. This review aims to gather recent information regarding bioactive properties of carotenoids and highlight pharmaceutical and health beneficial effects of carotenoids for the poultry industry. Additionally, it explores the importance of carotenoids as alternative feed ingredients for poultry to boost the production performance and replace synthetic medicine and nutrients.

Polarity shifting marked by various linguistic structures has been a challenge to automatic sentiment classification. In this paper, we propose a machine learning approach to incorporate polarity shifting information into a document-level sentiment classification system. First, a feature selection method is adopted to automatically generate the training data for a binary classifier on polarity shifting detection of sentences. Then, by using the obtained binary classifier, each document in the original polarity classification training data is split into two partitions, polarity-shifted and polarity-unshifted, which are used to train two base classifiers respectively for further classifier combination. The experimental results across four different domains demonstrate the effectiveness of our approach.

No abstract