Co-occurrence information between words is the basis of training word embeddings; besides, Chinese characters are composed of subcharacters, words made up by the same characters or subcharacters usually have similar semantics, but this internal substructure information is usually neglected in popular models. In this paper, we propose a novel method for learning Chinese word embeddings, which takes full use of external co-occurrence context information and internal substructure information. We represent each word as a bag of subcharacter n-grams, and our model learns the vector representation corresponding to the word and its subcharacter n-grams. The final word embeddings are represented as the sum of these two kinds of vector representation, which makes the learned word embeddings can take into account both the internal structure information and external co-occurrence information possible. The experiments show that our method outperforms state-of-the-art performance on benchmarks.INDEX TERMS Chinese word embedding, subcharacter, n-gram, language model.

No abstract

In this paper, a sequence-to-sequence based hybrid neural network model is proposed for abstractive summarization. Our method utilizes Bi-directional Long Short-Term Memory (Bi-LSTM) and multi-level dilated convolutions (MDC) to capture the global semantic information and semantic-unit level information, respectively. In decoding phrase, our model generates words according to summary relevant information captured by attention mechanism. Experiment shows that this proposed model outperforms several strong baselines on both of Gigawords corpus and DUC-2004 task.

Domain knowledge of hierarchical task network (HTN) usually involves logical expressions with predicates. One needs to master two different languages which are used to describe domain knowledge and implement planner. This has presented enormous challenges for most programmers who are not familiar with logical expressions. To solve the problem a method of state variable representation from the programmer’s point of view is introduced. This method has powerful expressivity and can unify the representations of domain knowledge and planning algorithm. In Pyhop a HTN planner written in Python, methods and operators are all as ordinary Python functions rather than using a special-purpose language. Pyhop uses a Python object that contains variable bindings and does not include a horn-clause inference engine for evaluating preconditions of operators and methods. By taking a simple travel-planning problem, it shows that the method is easy to understand and integrate planning into ordinary programming.

In order to solve the problem of lack of effective methods for ontology inconsistency, a user preferences-oriented ontology alignment repair model is proposed. This model uses 0-1 linear programming method to minimize the remove cost; the structure and source of ontology are used to measure the axiom of importance; Finally, by choosing the minimal conflict sets and the user preferences limit repair strategy, the purpose of eliminating inconsistency, reducing semantic loss and guaranteeing credibility is achieved. The experimental results show that this method can effectively solve the problem of ontology inconsistency, and the restored ontology is more suitable for user preferences than traditional methods.INDEX TERMS 0-1 linear programming, axiomatic measure, ontology inconsistency, user preferences.