Recent research has made impressive progress in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information omission in our daily conversation, making it hard for machines to understand the real intention. In this paper, we propose rewriting the human utterance as a pre-process to help multi-turn dialgoue modelling. Each utterance is first rewritten to recover all coreferred and omitted information. The next processing steps are then performed based on the rewritten utterance. To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network. We show the proposed architecture achieves remarkably good performance on the utterance rewriting task. The trained utterance rewriter can be easily integrated into online chatbots and brings general improvement over different domains. 1

No abstract

Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems. However, these latent variables are highly randomized, leading to uncontrollable generated responses. In this paper, we propose a framework allowing conditional response generation based on specific attributes. These attributes can be either manually assigned or automatically detected. Moreover, the dialog states for both speakers are modeled separately in order to reflect personal features. We validate this framework on two different scenarios, where the attribute refers to genericness and sentiment states respectively. The experiment result testified the potential of our model, where meaningful responses can be generated in accordance with the specified attributes.

No abstract

Isoprenoids are a class of ubiquitous organic molecules synthesized from the five-carbon starter unit isopentenyl pyrophosphate (IPP). Comprising more than 30,000 known natural products, isoprenoids serve various important biological functions in many organisms. In bacteria, undecaprenyl pyrophosphate is absolutely required for the formation of cell wall peptidoglycan and other cell surface structures, while ubiquinones and menaquinones, both containing an essential prenyl moiety, are key electron carriers in respiratory energy generation. There is scant knowledge on the nature and regulation of bacterial isoprenoid pathways. In order to explore the cellular responses to perturbations in the mevalonate pathway, responsible for producing the isoprenoid precursor IPP in many gram-positive bacteria and eukaryotes, we constructed three strains of Staphylococcus aureus in which each of the mevalonate pathway genes is regulated by an IPTG (isopropyl-␤-D-thiogalactopyranoside)-inducible promoter. We used DNA microarrays to profile the transcriptional effects of downregulating the components of the mevalonate pathway in S. aureus and demonstrate that decreased expression of the mevalonate pathway leads to widespread downregulation of primary metabolism genes, an upregulation in virulence factors and cell wall biosynthetic determinants, and surprisingly little compensatory expression in other isoprenoid biosynthetic genes. We subsequently correlate these transcriptional changes with downstream metabolic consequences.