With the development of reinforcement learning technology, reinforcement learning is utilized in many areas. The real-value optimization problem is common and difficult in manufacturing. In this study, a memetic algorithm (called ACMA) with reinforcement learning mechanism is designed for solving real-value optimization problems. The multi-heuristic pool which contains various heuristic algorithms is employed in ACMA to realize the automatic configuration of global and local search algorithms via Q-learning. The process of ACMA is mainly divided into two phases, including the training phase and the testing phase. The effective heuristic algorithms are selected from the multi-heuristic pool during the training phase, and effective heuristic algorithms are learned in the testing phase. The ACMA, standard MA, and other algorithms are utilized to address CEC 2017 benchmark problems. The results show that ACMA is a potential algorithm to address real-value optimization problems.

Neural Machine Translation (NMT) systems encounter a significant challenge when translating a pro-drop ('pronoun-dropping') language (e.g., Chinese) to a non-pro-drop one (e.g., English), since the pro-drop phenomenon demands NMT systems to recover omitted pronouns.This unique and crucial task, however, lacks sufficient datasets for benchmarking.To bridge this gap, we introduce PROSE, a new benchmark featured in diverse pro-drop instances for document-level Chinese-English spoken language translation.Furthermore, we conduct an in-depth investigation of the prodrop phenomenon in spoken Chinese on this dataset, reconfirming that pro-drop reduces the performance of NMT systems in Chinese-English translation.To alleviate the negative impact introduced by pro-drop, we propose Mention-Aware Semantic Augmentation, a novel approach that leverages the semantic embedding of dropped pronouns to augment training pairs.Results from the experiments on four Chinese-English translation corpora show that our proposed method outperforms existing methods regarding omitted pronoun retrieval and overall translation quality.

Topic segmentation aims to detect topic boundaries and split automatic speech recognition transcriptions (e.g., meeting transcripts) into segments that are bounded by thematic meanings.In this work, we propose M 3 Seg, a novel Maximum-Minimum Mutual information paradigm for linear topic segmentation without using any parallel data.Specifically, by employing sentence representations provided by pre-trained language models, M 3 Seg first learns a region-based segment encoder based on the maximization of mutual information between the global segment representation and the local contextual sentence representation.Secondly, an edge-based boundary detection module aims to segment the whole by topics based on minimizing the mutual information between different segments.Experiment results on two public datasets demonstrate the effectiveness of M 3 Seg, which outperform the state-of-the-art methods by a significant (18%-37% improvement) margin.

Online healthcare consultation offers people a convenient way to consult doctors. In this paper, we aim at building a generative dialog system for Chinese healthcare consultation. As the original Seq2seq architecture tends to suffer the issue of generating low-quality responses, the multi-source Seq2seq architecture generating more informative responses is much more preferred in this task. The multi-source Seq2seq architecture takes advantage of retrieval techniques to obtain responses from the database, and then takes these responses alongside the user-issued question as input. However, some of the retrieved responses might be not much related to the user-issued question, resulting in the generation of unsatisfying responses that are not correct in diagnosis or instead provide inappropriate advice on prevention or treatment. Therefore, this paper proposes multi-source Seq2seq guided by knowledge (MSSGK) to handle this problem. MSSGK differs from the multi-source Seq2seq architecture in that domain knowledge, including disease labels and topic labels about prevention and treatment, is introduced into the response generation via a multi-task learning framework. To better exploit the domain knowledge, we propose three attention mechanisms to provide more appropriate guidance for response generation. Experimental results on a dataset of real-world healthcare consultation show the effectiveness of the proposed method.