Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn conversation generation have greatly promoted the research of open domain dialogue systems. However, understanding multiple single turn conversations is not equal to the understanding of multi turn dialogue due to the coherent and context dependent properties of human dialogue. Therefore, in open domain multi turn dialogue generation, it is essential to modeling the contextual semantics of the dialogue history rather than only according to the last utterance. Previous research had verified the effectiveness of the hierarchical recurrent encoder-decoder framework on open domain multi turn dialogue generation. However, using an RNN-based model to hierarchically encoding the utterances to obtain the representation of dialogue history still face the problem of a vanishing gradient. To address this issue, in this article, we proposed a static and dynamic attention-based approach to model the dialogue history and then generate open domain multi turn dialogue responses. Experimental results on the Ubuntu and Opensubtitles datasets verify the effectiveness of the proposed static and dynamic attention-based approach on automatic and human evaluation metrics in various experimental settings. Meanwhile, we also empirically verify the performance of combining the static and dynamic attentions on open domain multi turn dialogue generation.

Despite the success of existing works on single-turn conversation generation, taking the coherence in consideration, human conversing is actually a context-sensitive process. Inspired by the existing studies, this paper proposed the static and dynamic attention based approaches for context-sensitive generation of open-domain conversational responses. Experimental results on two public datasets show that the proposed static attention based approach outperforms all the baselines on automatic and human evaluation.

This paper presents an off-line simulation approach that aims to provide a model-based online control of a proposed intelligent fixturing system. The intelligent fixturing system is to adaptively adjust the clamping forces to optimal values during the machining process. Using the off-line simulation, an analytical fixture-workpiece model and an optimization method have been developed for the control of a fixturing system. This simulation can also be applied to evaluate the performance of a fixturing system and determine optimal clamping forces for a given fixture configuration. Experiments have been conducted to verify the proposed model. The fixturing system can be applied in a high-precision machining environment where the workpiece deformation due to over-clamping and improper machining is a major concern.